Query language filter for cross-language information retrieval

    公开(公告)号:US09824147B1

    公开(公告)日:2017-11-21

    申请号:US13781579

    申请日:2013-02-28

    Applicant: Google Inc.

    CPC classification number: G06F17/30864 G06F17/30669 G06F17/30696

    Abstract: A method of processing search queries, performed by a search server system, includes receiving, from a client system, a search query and an indicia of an application language associated with an application used at the client system to perform the search query. The search server system responds by identifying a first language and a first probability factor that specifies a likelihood that the search query is in the first language. In response to satisfaction of filter criteria, comprising a determination that the first language corresponds to the application language, the search server system translates the search query to a translated search query in a second language distinct from the application language, obtains search results for the translated search query, and conveys to the client system at least a subset of the search results for the translated search query.

    PREDICTING USER NEEDS FOR A PARTICULAR CONTEXT
    2.
    发明申请
    PREDICTING USER NEEDS FOR A PARTICULAR CONTEXT 有权
    预测用户对特定语境的需求

    公开(公告)号:US20160350383A1

    公开(公告)日:2016-12-01

    申请号:US14721613

    申请日:2015-05-26

    Applicant: Google Inc.

    Abstract: A computing system is described that identifies, based on search histories associated with a group of computing devices for a particular context, a task performed by users of the group of computing devices for the particular context. The computing system determines a first degree of likelihood of the task being performed by the users of the group of computing devices for the particular context and determines a second degree of likelihood of the task being performed by the users of the group of computing devices for a broader context that includes the particular context and at least one other context. Responsive to determining that the first degree of likelihood exceeds the second degree of likelihood by a threshold amount, and that a current context of a particular computing device corresponds to the particular context, the computing system transmits, to the particular computing device, information for completing the task for the particular context.

    Abstract translation: 描述了一种计算系统,其基于与用于特定上下文的一组计算设备相关联的搜索历史来识别由用于特定上下文的计算设备组的用户执行的任务。 计算系统确定由特定上下文的计算设备组的用户执行任务的第一程度的可能性,并且确定由该组计算设备的用户执行的任务的第二程度的可能性 包括特定上下文和至少一个其他上下文的更广泛的上下文。 响应于确定第一似然度超过第二可能度阈值量,并且特定计算设备的当前上下文对应于特定上下文,计算系统向特定计算设备发送用于完成的信息 特定上下文的任务。

Patent Agency Ranking