PREDICTING USER INTENT BASED ON ENTITY-TYPE SEARCH INDEXES

    公开(公告)号:US20190005089A1

    公开(公告)日:2019-01-03

    申请号:US15636199

    申请日:2017-06-28

    Abstract: An online system stores objects that may be accessed by users. The online system also stores indexes of terms related to different entity types of objects. When a user provides a search query, the online system compares the search terms with terms stored in the indexes. Based on the comparisons, the online system determines term features for entity types associated with an index. The online system provides the term features as inputs to a machine learning model. The machine learning model outputs a score for each entity type indicating a likelihood that the search query is for an object associated with the entity type. The machine learning model output is used by the online system to select one or more entity types that the user is likely searching for. The online system offers objects of the likely entity types to the user as results of the search query.

    SYSTEMS AND METHODS FOR PERFORMING SMART SEARCHES
    2.
    发明申请
    SYSTEMS AND METHODS FOR PERFORMING SMART SEARCHES 审中-公开
    执行智能搜索的系统和方法

    公开(公告)号:US20140019439A1

    公开(公告)日:2014-01-16

    申请号:US13935267

    申请日:2013-07-03

    CPC classification number: G06F16/9038

    Abstract: A multi-tenant server system for executing search queries includes a database that stores multi-tenant data including data objects having associated data records for a plurality of users associated with a plurality of tenants, and a server system including a processor. The processor is configured to execute a method including the steps of applying search queries to the multi-tenant database and providing a search result set including a plurality of data objects each having at least one data record. The method further includes reordering the search result set according to predetermined scoping criteria based on individual user histories, including recency and frequency metrics, to produce a reordered search result set. The reordered set is filtered based on predetermined permission criteria associated with each user, and displayed.

    Abstract translation: 用于执行搜索查询的多租户服务器系统包括存储多租户数据的数据库,所述多租户数据包括具有与多个租户相关联的多个用户的相关联的数据记录的数据对象,以及包括处理器的服务器系统。 处理器被配置为执行一种方法,包括以下步骤:将搜索查询应用于多租户数据库,并提供包括多个数据对象的搜索结果集,每个数据对象具有至少一个数据记录。 该方法还包括根据基于个体用户历史(包括新近度和频率度量)的预定范围标准重新排序搜索结果集,以产生重新排序的搜索结果集。 基于与每个用户相关联的预定许可准则对重新排序的组进行过滤,并显示。

Patent Agency Ranking