Presenting previously selected search results

    公开(公告)号:US10061806B2

    公开(公告)日:2018-08-28

    申请号:US15293946

    申请日:2016-10-14

    Applicant: Google LLC

    CPC classification number: G06F16/2455 G06F16/248 G06F16/3349

    Abstract: The disclosed subject matter provides methods and systems for presenting previously selected search results to a user. A first previously selected search result may be obtained from a first search provider. The first previously selected search result may be a first result, selected by a user, of a first prior search query executed by the first search provider. A second previously selected search result may be obtained from a second search provider, and the second previously selected search result may be a second result, selected by the user, of a second prior search query executed by the second search provider. Next, the first and second previously selected search results may be presented in an interface associated with a third search provider.

    METHOD AND SERVER FOR CLASSIFYING QUERIES
    7.
    发明申请

    公开(公告)号:US20170154105A1

    公开(公告)日:2017-06-01

    申请号:US15319753

    申请日:2015-07-17

    Applicant: Maluuba Inc.

    CPC classification number: G06F16/35 G06F16/3331 G06F16/3349

    Abstract: A server, method, and non-transitory computer readable medium for classifying queries based on contextual information are provided. The server includes a network interface, a memory storage unit and a processor. The method involves receiving a plurality of queries, analyzing the queries and determining a likelihood divergence and selecting a domain. The non-transitory computer readable medium is encoded with codes to direct a processor to carry out the method.

    Machine Learning Model for Level-Based Categorization of Natural Language Parameters
    8.
    发明申请
    Machine Learning Model for Level-Based Categorization of Natural Language Parameters 审中-公开
    自然语言参数基于级别分类的机器学习模型

    公开(公告)号:US20160071022A1

    公开(公告)日:2016-03-10

    申请号:US14476912

    申请日:2014-09-04

    Abstract: A mechanism is provided in a data processing system for categorizing a user providing a text input. The mechanism receives an input text written by a user and determines a set of features associated with the input text. The mechanism processes the input text and the set of features by a detection model. The detection model comprises a plurality of detectors corresponding to a plurality of categories. Each of the plurality of detectors determines whether the user fits a respective category based on the input text and the set of features. The mechanism categorizes the user into one or more of the plurality of categories based on a result of processing the input text and the set of features by the detection model.

    Abstract translation: 在用于对提供文本输入的用户进行分类的数据处理系统中提供一种机制。 该机制接收用户写入的输入文本并确定与输入文本相关联的一组特征。 该机制通过检测模型处理输入文本和特征集。 检测模型包括对应于多个类别的多个检测器。 多个检测器中的每个检测器基于输入文本和特征集来确定用户是否适合相应的类别。 该机构基于通过检测模型处理输入文本和特征集合的结果,将用户分类为多个类别中的一个或多个。

    ASSISTANCE METHOD FOR A CALL CENTER OPERATOR
    9.
    发明申请
    ASSISTANCE METHOD FOR A CALL CENTER OPERATOR 审中-公开
    呼叫中心操作员的辅助方法

    公开(公告)号:US20120096024A1

    公开(公告)日:2012-04-19

    申请号:US13256411

    申请日:2010-02-12

    CPC classification number: G06F16/3329 G06F16/3349

    Abstract: The present invention pertains to method for assisting an operator from a call center who must respond to a request for information (200), received by that call center, by means of a standard response stored in a base (306, 310) of standard responses, this base (306, 310) of standard responses being automatically used in order to provide the operator (302) with possible responses to the request for information (200), characterized in that it comprises the following steps: the step of identifying elements representative of the request (200) for information, the step of using the elements representative of the request (200) for information, both to select a preferred response (201) to the request (200) and to identify alternative responses (202, 204, 206) transmitted beforehand by operators with respect to prior requests identified by rep selected elements similar to the represented elements of the request for information, and the step of transmitting to the operator (302) the request for information (200), the selected response (201), and the alternative responses (202, 204, 206).

    Abstract translation: 本发明涉及一种用于协助来自呼叫中心的运营商的方法,该呼叫中心必须通过存储在标准响应的基站(306,310)中的标准响应来响应由该呼叫中心接收到的信息请求(200) 标准响应的该基座(306,310)被自动使用以便向操作者(302)提供对信息请求(200)的可能响应,其特征在于,其包括以下步骤:识别元件代表的步骤 (200)用于信息的步骤,使用表示请求(200)的元素作为信息的步骤,既可以选择对请求(200)的优选响应(201)并且识别替代响应(202,204, 206),由所述操作者预先通过由所述代表所选择的元素识别的先前请求发送,所述先前请求类似于所述信息请求的所表示的元素,并且向所述操作者(302)发送所述请求fo r信息(200),所选择的响应(201)和备选响应(202,204,206)。

    SEARCH ENGINE PROVIDING PERSISTENT SEARCH FUNCTIONALITY OVER MULTIPLE SEARCH QUERIES AND METHOD FOR OPERATING THE SAME
    10.
    发明申请
    SEARCH ENGINE PROVIDING PERSISTENT SEARCH FUNCTIONALITY OVER MULTIPLE SEARCH QUERIES AND METHOD FOR OPERATING THE SAME 审中-公开
    搜索引擎提供多项搜索查询及其操作方法的搜索功能

    公开(公告)号:US20070112741A1

    公开(公告)日:2007-05-17

    申请号:US11559438

    申请日:2006-11-14

    CPC classification number: G06F16/9535 G06F16/3349

    Abstract: In one embodiment, a method of operating a search engine comprises: initiating a continuous search state from a user; receiving multiple search queries during the continuous search state; and providing search results to the user, wherein the providing filters search results previously presented to the user in response to prior search queries during the continuous search state.

    Abstract translation: 在一个实施例中,一种操作搜索引擎的方法包括:从用户发起连续搜索状态; 在连续搜索状态期间接收多个搜索查询; 以及向用户提供搜索结果,其中提供过滤器在连续搜索状态期间响应于先前的搜索查询而先前呈现给用户的搜索结果。

Patent Agency Ranking