知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

58 records (took 0.021 seconds)

    Selecting textual representations for entity attribute values
    42.
    发明授权
    Selecting textual representations for entity attribute values 有权

    公开(公告)号：US10685073B1

    公开(公告)日：2020-06-16

    申请号：US15669799

    申请日：2017-08-04

    Applicant: Google LLC

    Inventor： Eyal Segalis ,  Yaniv Leviathan ,  Yossi Matias ,  Gal Chechik ,  Yoav Tzur ,  Ran El Manor

    IPC: G06F17/30 ,  G06F16/9535 ,  G06F16/335 ,  G06F16/35

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting textual representations for entity attribute values. One of the methods includes receiving, for presentation to a user, data identifying a relevant entity and a respective presentation attribute value for each of a plurality of presentation attributes associated with the relevant entity; obtaining user profile data for the user; selecting a respective textual representation for each of the presentation attribute values, wherein selecting the textual representations comprises selecting a first alternative textual representation for a first presentation attribute value based on the user profile data; and providing data identifying the entity and the textual representations for presentation to the user.

    Third party search applications for a search system
    45.
    发明授权
    Third party search applications for a search system 有权

    公开(公告)号：US10289618B2

    公开(公告)日：2019-05-14

    申请号：US16029758

    申请日：2018-07-09

    Applicant: Google LLC

    Inventor： Michael Fink ,  Niv Efron ,  Eyal Fink ,  Alex Gontmakher ,  Anatoly Vorobey ,  Yossi Matias ,  Jack Wright Menzel ,  Asaph Arnon

    IPC: G06F17/30 ,  G06F16/2455 ,  G06F16/951 ,  G06F21/53 ,  G06F21/74

    Abstract: Systems and methods offer a search system with third-party provided search applications that are triggered in response to specified queries and run at the search system. For example, a method may include determining that a query triggers a third party search application hosted at the search system, executing the third party search application at the search system using computer-instructions obtained from the third party to generate and format a third-party formatted answer for the query, and providing the third-party formatted answer as a search result for the query. The third party may provide the query template, parameter attributes, if any, and the third party formatted answer. The third party search application is stored at the search system and may include the query template, a data store, the parameter attributes, and computer-instructions for accessing the data store using the parameter.

    LARGE LANGUAGE MODEL OUTPUT ENTAILMENT
    46.
    发明申请
    LARGE LANGUAGE MODEL OUTPUT ENTAILMENT 有权

    公开(公告)号：US20250094456A1

    公开(公告)日：2025-03-20

    申请号：US18887751

    申请日：2024-09-17

    Applicant: GOOGLE LLC

    Inventor： Kelvin Gu ,  Zhuyun Dai ,  Panupong Pasupat ,  Chen Elkind ,  Eran Ofek ,  Hagai Taitelbaum ,  Mukund Sundararajan ,  Vered Cohen ,  Itay Karo ,  Norbert Kalb ,  Yossi Matias ,  Tej Toor ,  Teghan Tracy

    IPC: G06F16/332 ,  G06F16/33 ,  G06F16/35

    Abstract: Implementations are described herein for identifying potentially false information in generative model output by performing entailment evaluation of generative model output. In various implementations, data indicative of a query may be processed to generate generative model output. Textual fragments may be extracted from the generative model output, and a subset of the textual fragments may be classified as being suitable for textual entailment analysis. Textual entailment analysis may be performed on each textual fragment of the subset, including formulating a search query based on the textual fragment, retrieving document(s) responsive to the search query, and processing the textual fragment and the document(s) using entailment machine learning model(s) to generate prediction(s) of whether the at least one document corroborates or contradicts the textual fragment. When natural language (NL) responsive to the query is rendered at a client device, annotation(s) may be rendered to express the prediction(s).

Patent Agency Ranking