利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.017 秒)

    Generating multi-perspective responses by assistant systems
    2.
    发明授权
    Generating multi-perspective responses by assistant systems 有权

    公开(公告)号：US11263276B1

    公开(公告)日：2022-03-01

    申请号：US16176312

    申请日：2018-10-31

    申请人： Meta Platforms, Inc.

    发明人： Emmanouil Koukoumidis ,  Michael Robert Hanson ,  Rajen Subba ,  Heidi Young ,  Rushin Shah ,  Jinsong Yu ,  Benoit F. Dumoulin ,  Jeremy Gillmor Kahn ,  Chandrasekhar Iyer

    IPC分类号： G06F16/00 ,  G06F16/951 ,  G06N20/00 ,  G06F40/40

    摘要： In one embodiment, a method includes receiving a user query from a client system associated with a first user, determining a plurality of dialog-intents, each being associated with a particular agent of a plurality of agents, executing a plurality of tasks corresponding to the user query via the plurality of agents corresponding to the plurality of dialog-intents, receiving a plurality of execution results corresponding to the plurality of tasks from the plurality of agents, respectively, selecting two or more of the plurality of execution results for combination, generating a multi-perspective response based on the selected execution results by a stitching model, wherein the multi-perspective response comprises a natural-language response combining the selected execution results, and sending instructions for presenting the multi-perspective response to the first user to the client system in response to the user query.

    Predictive Injection of Conversation Fillers for Assistant Systems
    8.
    发明申请
    Predictive Injection of Conversation Fillers for Assistant Systems 有权

    公开(公告)号：US20220166733A1

    公开(公告)日：2022-05-26

    申请号：US17666439

    申请日：2022-02-07

    申请人： Meta Platforms, Inc.

    发明人： Emmanouil Koukoumidis ,  Michael Robert Hanson ,  Mohsen M. Agsen

    IPC分类号： H04L51/02 ,  H04L51/52 ,  G06N20/00 ,  G06F40/295

    摘要： In one embodiment, a method includes, by one or more computing systems, receiving, at the client system, a first user input, processing, by the client system, the first user input to provide an initial response by identifying one or more entities referenced by the first user input and providing, by the client system, the initial response, where the initial response comprises a conversational filler referencing at least one of the one or more identified entities, processing the first user input to provide a complete response by identifying, by the client system, one or more intents and one or more slots associated with the first user input based on a semantic analysis by a natural-language understanding module and providing, by the client system, the complete response subsequent to the initial response, where the complete response is based on the one or more intents and the one or more slots.