Using popularity data for ranking
    2.
    发明授权
    Using popularity data for ranking 有权
    使用流行度数据进行排名

    公开(公告)号:US07783632B2

    公开(公告)日:2010-08-24

    申请号:US11266026

    申请日:2005-11-03

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/30864

    摘要: A unique ranking system and method that facilitates improving the ranking and ordering of objects to further enhance the quality, accuracy, and delivery of search results in response to a search query. The system and method involve monitoring and tracking an object in terms of the number of times it's been accessed and optionally by whom, when, for how long, and an access rate. The user's interaction with the object can be tracked as well. By tracking the objects, a popularity measure can be determined. Popularity based rankings can be computed based on the popularity measure or some function thereof. The popularity measure can be affected by the access time, who accessed it, access duration or the user's interaction with the object upon access. The popularity based rankings can be utilized by a search component to improve the quality and retrieval of search results.

    摘要翻译: 一种独特的排名系统和方法,有助于提高对象的排序和排序,以进一步提高搜索结果的质量,准确性和传递以响应搜索查询。 该系统和方法涉及根据访问次数来监视和跟踪对象,并且可选地由谁,何时,多长时间和访问速率来跟踪对象。 也可以跟踪用户与对象的交互。 通过跟踪对象,可以确定流行度量。 基于流行度的排名可以基于流行度量或其一些功能来计算。 流行度量可能受访问时间,访问时间,访问持续时间或用户与访问对象的交互的影响。 搜索组件可以利用基于流行度的排名来提高搜索结果的质量和检索。

    Efficiency of training for ranking systems based on pairwise training with aggregated gradients
    3.
    发明授权
    Efficiency of training for ranking systems based on pairwise training with aggregated gradients 有权
    基于与聚合梯度成对训练的排名系统的培训效率

    公开(公告)号:US07617164B2

    公开(公告)日:2009-11-10

    申请号:US11378086

    申请日:2006-03-17

    IPC分类号: G06F15/18 G06G7/00 G06N3/02

    CPC分类号: G06N99/005 Y10S707/99935

    摘要: The subject disclosure pertains to systems and methods for facilitating training of machine learning systems utilizing pairwise training. The number of computations required during pairwise training is reduced by grouping the computations. First, a score is generated for each retrieved data item. During processing of the data item pairs, the scores of the data items in the pair are retrieved and used to generate a gradient for each data item. Once all of the pairs have been processed, the gradients for each data item are aggregated and the aggregated gradients are used to update the machine learning system.

    摘要翻译: 本发明涉及利用成对训练促进训练机器学习系统的系统和方法。 通过对计算进行分组,减少了成对训练中所需的计算次数。 首先,为每个检索到的数据项生成分数。 在数据项对的处理期间,检索对中的数据项的分数,并用于为每个数据项生成一个渐变。 一旦所有的对已被处理,每个数据项的渐变被聚合,聚合的梯度被用来更新机器学习系统。

    Feature-value attachment, reranking and filtering for advertisements

    公开(公告)号:US10346854B2

    公开(公告)日:2019-07-09

    申请号:US11948721

    申请日:2007-11-30

    IPC分类号: G06Q30/02

    摘要: An approach is provided for associating structured information as feature-value pairs with advertisements at an advertisement system that provides advertisements for presentation with primary content. Feature-value pairs corresponding with advertisements describe features of the products or services associated with the advertisements. The feature-value pairs may be used by the advertisement system in a number of different manners, including, among other things: using the feature-value pairs during selection of advertisements for presentation with primary content: allowing users to sort and/or filter advertisements during presentation with primary content based on the associated feature-value pairs; exposing additional information with the advertisements; facilitating fraud detection for the advertisement system; and enabling a hybrid pricing model.

    PROGRESSIVE PRICING SCHEMES FOR ADVERTISEMENTS
    6.
    发明申请
    PROGRESSIVE PRICING SCHEMES FOR ADVERTISEMENTS 审中-公开
    广告推广计划

    公开(公告)号:US20090144207A1

    公开(公告)日:2009-06-04

    申请号:US11949548

    申请日:2007-12-03

    IPC分类号: G06F17/00 G06Q20/00

    CPC分类号: G06Q30/02 G06Q30/0283

    摘要: Systems, methods, and computer-readable media for calculating charges for advertisements are provided. The historical performance (such as CTR) of an online advertisement is utilized to calculate accurate performance prediction, in turn used to calculate the current cost per selection (click-through) of the advertisement. The current cost per selection may be multiplied by the total number of times the advertisement has been presented to user(s) to determine the adjusted revenue total for the advertisement. In embodiments, the charge due for the advertisement is the adjusted revenue total for the advertisement less the amount of revenue previously received for the advertisement.

    摘要翻译: 提供了用于计算广告费用的系统,方法和计算机可读介质。 使用在线广告的历史表现(如点击率)来计算准确的性能预测,反过来用于计算广告的每个选择(点击)的当前成本。 每个选择的当前成本可以乘以广告被呈现给用户的总次数,以确定广告的调整收入总额。 在实施例中,广告的费用是广告的经调整的收入总额减去先前为广告接收的收入的数量。

    Attention estimation through incremental impression interaction for precise advertisement monetization
    7.
    发明申请
    Attention estimation through incremental impression interaction for precise advertisement monetization 审中-公开
    通过增量印象交互来注意评估,以进行精确的广告营利

    公开(公告)号:US20080243610A1

    公开(公告)日:2008-10-02

    申请号:US11729059

    申请日:2007-03-28

    IPC分类号: G06Q30/00 G06F3/048

    CPC分类号: G06Q30/02 G06Q30/0277

    摘要: An advertising package can contain multiple levels of advertisements ranging from small, unobtrusive ads at initial levels, to larger, more complex and more informative ads at subsequent levels. Viewers of a web page, or users of an ad-sponsored program, can initially be presented with a first level advertisement. User triggering actions can cause the display of a subsequent level advertisements that can provide further information without leaving the context of the web page or ad-sponsored program. The levels of advertisements displayed to a user can offer a more precise measure of user interest, and can be the basis by which future ad packages are tuned, and can be the basis of more tiered financial agreements between the advertiser and the publisher.

    摘要翻译: 广告套餐可以包含多个级别的广告,从初级阶段的小型,不引人注目的广告到随后级别的更大,更复杂和更丰富的广告。 网页的观众或广告赞助节目的用户最初可以呈现第一级广告。 用户触发动作可能导致显示可以提供更多信息的后续级别广告,而不会丢弃网页或广告赞助程序的上下文。 向用户展示的广告级别可以提供更精确的用户兴趣度量,并且可以作为未来广告包的调整基础,并且可以作为广告主和发布者之间更多层次的财务协议的基础。

    Selecting directly bid upon advertisements for display
    8.
    发明授权
    Selecting directly bid upon advertisements for display 有权
    选择直接投标广告进行展示

    公开(公告)号:US08370343B2

    公开(公告)日:2013-02-05

    申请号:US11395850

    申请日:2006-03-31

    IPC分类号: G06F7/00 G06Q30/00

    CPC分类号: G06Q30/02

    摘要: Methods and systems in search marketing which permit advertisers to provide advertisements to a search engine, as well as bids associated with the advertisements themselves, are provided. Advertisements are selected for presentation when they are determined to be relevant and payment for presentation is due only upon the conditions of the bid being met. If desired, advertisers may be permitted to provide, in addition to an advertisement, one or more destination pages associated with selection of the advertisement. In this case, relevance can be determined not only on the basis of the content of the advertisement itself, but also on the content of the destination page(s).

    摘要翻译: 提供允许广告商向搜索引擎提供广告以及与广告本身相关联的出价的搜索营销中的方法和系统。 当广告被确定为相关性时才被选择进行展示,并且只有在符合投标条件的情况下才能付款。 如果需要,可以允许广告商除了广告之外还提供与选择广告相关联的一个或多个目的地页面。 在这种情况下,不仅可以基于广告本身的内容,还可以根据目的地页面的内容来确定相关性。

    Entity-specific tuned searching
    9.
    发明授权
    Entity-specific tuned searching 有权
    实体特定调谐搜索

    公开(公告)号:US07739270B2

    公开(公告)日:2010-06-15

    申请号:US11005989

    申请日:2004-12-07

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30867

    摘要: The present invention leverages relevance data to provide enhanced search query results based on relevancy to a specific entity via an entity-specific tunable search. This allows an entity to retrieve information that is of more value to that entity, in a faster and more efficient manner. The entity itself can be an individual user, a grouping of users, and/or an enterprise and the like. In one instance of the present invention, entity-specific relevance information is determined via employment of similarity of the entity to another entity or group of entities. Interest levels and/or satisfaction levels of similar entities can also be utilized along with similarity information to facilitate in deriving the relevance information.

    摘要翻译: 本发明利用相关性数据,以通过特定于实体的可调搜索来提供基于与特定实体的相关性的增强的搜索查询结果。 这允许实体以更快更有效的方式检索对该实体更有价值的信息。 实体本身可以是单个用户,用户组和/或企业等。 在本发明的一个实例中,通过使用实体与另一实体或实体组的相似度来确定实体相关信息。 类似实体的兴趣水平和/或满意度水平也可以与相似性信息一起使用以促进相关性信息的导出。

    FEATURE-VALUE ATTACHMENT, RERANKING AND FILTERING FOR ADVERTISEMENTS
    10.
    发明申请
    FEATURE-VALUE ATTACHMENT, RERANKING AND FILTERING FOR ADVERTISEMENTS 审中-公开
    特征价值附件,广告的过滤和过滤

    公开(公告)号:US20090144141A1

    公开(公告)日:2009-06-04

    申请号:US11948721

    申请日:2007-11-30

    IPC分类号: G06Q30/00

    CPC分类号: G06Q30/02 G06Q30/0242

    摘要: An approach is provided for associating structured information as feature-value pairs with advertisements at an advertisement system that provides advertisements for presentation with primary content. Feature-value pairs corresponding with advertisements describe features of the products or services associated with the advertisements. The feature-value pairs may be used by the advertisement system in a number of different manners, including, among other things: using the feature-value pairs during selection of advertisements for presentation with primary content: allowing users to sort and/or filter advertisements during presentation with primary content based on the associated feature-value pairs; exposing additional information with the advertisements; facilitating fraud detection for the advertisement system; and enabling a hybrid pricing model.

    摘要翻译: 提供了一种用于将结构化信息作为特征值对与在提供用于呈现主要内容的广告的广告系统的广告相关联的方法。 与广告相对应的特征值对描述与广告相关联的产品或服务的特征。 特征值对可以由广告系统以多种不同的方式使用,其中包括:在选择广告期间使用特征值对来呈现主要内容:允许用户对广告进行排序和/或过滤 在基于相关特征值对的主要内容呈现期间; 暴露广告附加信息; 促进广告系统的欺诈检测; 并实现混合定价模型。