SUPPLEMENTING A TRAINED MODEL USING INCREMENTAL DATA IN MAKING ITEM RECOMMENDATIONS
    1.
    发明申请
    SUPPLEMENTING A TRAINED MODEL USING INCREMENTAL DATA IN MAKING ITEM RECOMMENDATIONS 有权
    在制作项目建议书中使用增量数据补充培训模型

    公开(公告)号:US20130024318A1

    公开(公告)日:2013-01-24

    申请号:US13618647

    申请日:2012-09-14

    IPC分类号: G06Q30/00

    CPC分类号: G06N99/005 G06N5/045

    摘要: Incremental training data is used to supplement a trained model to provide personalized recommendations for a user. The personalized recommendations can be made by taking into account the user's behavior, such as, without limitation, the user's short and long term web page interactions, to identify item recommendations. A trained model is generated from training data indicative of the web page interaction data collected from a plurality of users. Incremental training data indicative of other web page interaction data can be used to supplement the trained model, or in place of the trained model. Incremental training data can be indicative of user behavior collected more recently than the data used to train the model, for example.

    摘要翻译: 增量训练数据用于补充训练有素的模型,为用户提供个性化的建议。 可以通过考虑用户的行为(例如但不限于用户的短期和长期网页交互)来识别项目建议来进行个性化建议。 从训练数据生成训练模型,指示从多个用户收集的网页交互数据。 可以使用指示其他网页交互数据的增量训练数据来补充训练的模型,或代替训练的模型。 例如,增量训练数据可以指示比用于训练模型的数据最近收集的用户行为。

    SUPPLEMENTING A TRAINED MODEL USING INCREMENTAL DATA IN MAKING ITEM RECOMMENDATIONS
    2.
    发明申请
    SUPPLEMENTING A TRAINED MODEL USING INCREMENTAL DATA IN MAKING ITEM RECOMMENDATIONS 有权
    在制作项目建议书中使用增量数据补充培训模型

    公开(公告)号:US20110029464A1

    公开(公告)日:2011-02-03

    申请号:US12533632

    申请日:2009-07-31

    IPC分类号: G06F15/18 G06N5/02

    CPC分类号: G06N99/005 G06N5/045

    摘要: Incremental training data is used to supplement a trained model to provide personalized recommendations for a user. The personalized recommendations can be made by taking into account the user's behavior, such as, without limitation, the user's short and long term web page interactions, to identify item recommendations. A trained model is generated from training data indicative of the web page interaction data collected from a plurality of users. Incremental training data indicative of other web page interaction data can be used to supplement the trained model, or in place of the trained model. Incremental training data can be indicative of user behavior collected more recently than the data used to train the model, for example.

    摘要翻译: 增量训练数据用于补充训练有素的模型,为用户提供个性化的建议。 可以通过考虑用户的行为(例如但不限于用户的短期和长期网页交互)来识别项目建议来进行个性化建议。 从训练数据生成训练模型,指示从多个用户收集的网页交互数据。 可以使用指示其他网页交互数据的增量训练数据来补充训练的模型,或代替训练的模型。 例如,增量训练数据可以指示比用于训练模型的数据最近收集的用户行为。

    Supplementing a trained model using incremental data in making item recommendations
    3.
    发明授权
    Supplementing a trained model using incremental data in making item recommendations 有权
    使用增量数据来补充训练有素的模型来提出项目建议

    公开(公告)号:US08762318B2

    公开(公告)日:2014-06-24

    申请号:US13618647

    申请日:2012-09-14

    IPC分类号: G06N5/04 G06N99/00

    CPC分类号: G06N99/005 G06N5/045

    摘要: Incremental training data is used to supplement a trained model to provide personalized recommendations for a user. The personalized recommendations can be made by taking into account the user's behavior, such as, without limitation, the user's short and long term web page interactions, to identify item recommendations. A trained model is generated from training data indicative of the web page interaction data collected from a plurality of users. Incremental training data indicative of other web page interaction data can be used to supplement the trained model, or in place of the trained model. Incremental training data can be indicative of user behavior collected more recently than the data used to train the model, for example.

    摘要翻译: 增量训练数据用于补充训练有素的模型,为用户提供个性化的建议。 可以通过考虑用户的行为(例如但不限于用户的短期和长期网页交互)来识别项目建议来进行个性化建议。 从训练数据生成训练模型,指示从多个用户收集的网页交互数据。 可以使用指示其他网页交互数据的增量训练数据来补充训练的模型,或代替训练的模型。 例如,增量训练数据可以指示比用于训练模型的数据最近收集的用户行为。

    Supplementing a trained model using incremental data in making item recommendations
    4.
    发明授权
    Supplementing a trained model using incremental data in making item recommendations 有权
    使用增量数据来补充训练有素的模型来提出项目建议

    公开(公告)号:US08326777B2

    公开(公告)日:2012-12-04

    申请号:US12533632

    申请日:2009-07-31

    IPC分类号: G06F15/18 G06N5/02

    CPC分类号: G06N99/005 G06N5/045

    摘要: Incremental training data is used to supplement a trained model to provide personalized recommendations for a user. The personalized recommendations can be made by taking into account the user's behavior, such as, without limitation, the user's short and long term web page interactions, to identify item recommendations. A trained model is generated from training data indicative of the web page interaction data collected from a plurality of users. Incremental training data indicative of other web page interaction data can be used to supplement the trained model, or in place of the trained model. Incremental training data can be indicative of user behavior collected more recently than the data used to train the model, for example.

    摘要翻译: 增量训练数据用于补充训练有素的模型,为用户提供个性化的建议。 可以通过考虑用户的行为(例如但不限于用户的短期和长期网页交互)来识别项目建议来进行个性化建议。 从训练数据生成训练模型,指示从多个用户收集的网页交互数据。 可以使用指示其他网页交互数据的增量训练数据来补充训练的模型,或代替训练的模型。 例如,增量训练数据可以指示比用于训练模型的数据最近收集的用户行为。

    System for optimizing ad performance at campaign running time
    5.
    发明授权
    System for optimizing ad performance at campaign running time 有权
    用于在广告系列运行时优化广告效果的系统

    公开(公告)号:US08645205B2

    公开(公告)日:2014-02-04

    申请号:US12241726

    申请日:2008-09-30

    IPC分类号: G06Q30/00

    CPC分类号: G06Q30/02 G06Q30/0244

    摘要: A system and method are disclosed for optimizing the performance of an advertisement. The advertisement may be targeted based on correlations between advertisements and/or users. The correlations may be used to improve the click-through rate of advertisements. As data is collected and feedback is received, the correlation between ads and users may be updated, so that an advertiser's campaign can optimize its targeting of users.

    摘要翻译: 公开了一种用于优化广告的性能的系统和方法。 可以基于广告和/或用户之间的相关性来对广告进行定位。 相关性可用于提高广告的点击率。 收集数据并收到反馈后,可能会更新广告和用户之间的相关性,以便广告客户的广告系列可以优化用户的定位。

    SYSTEM FOR OPTIMIZING AD PERFORMANCE AT CAMPAIGN RUNNING TIME
    6.
    发明申请
    SYSTEM FOR OPTIMIZING AD PERFORMANCE AT CAMPAIGN RUNNING TIME 有权
    在运动时间优化AD性能的系统

    公开(公告)号:US20100082423A1

    公开(公告)日:2010-04-01

    申请号:US12241726

    申请日:2008-09-30

    IPC分类号: G06Q30/00

    CPC分类号: G06Q30/02 G06Q30/0244

    摘要: A system and method are disclosed for optimizing the performance of an advertisement. The advertisement may be targeted based on correlations between advertisements and/or users. The correlations may be used to improve the click-through rate of advertisements. As data is collected and feedback is received, the correlation between ads and users may be updated, so that an advertiser's campaign can optimize its targeting of users.

    摘要翻译: 公开了一种用于优化广告的性能的系统和方法。 可以基于广告和/或用户之间的相关性来对广告进行定位。 相关性可用于提高广告的点击率。 收集数据并收到反馈后,可能会更新广告和用户之间的相关性,以便广告客户的广告系列可以优化用户的定位。

    Predicting item-item affinities based on item features by regression
    7.
    发明授权
    Predicting item-item affinities based on item features by regression 有权
    通过回归预测基于项目特征的项目项目亲和度

    公开(公告)号:US08442929B2

    公开(公告)日:2013-05-14

    申请号:US12613503

    申请日:2009-11-05

    IPC分类号: G06F17/00 G06N5/00

    CPC分类号: G06Q10/04

    摘要: Two items are determined to be similar to each not only based on previous actual user behavior, but also based on the observed relatedness of the characteristics of those two items. A first characteristic and a second characteristic are determined to have some affinity for each other if a high proportion of users who select items having the first characteristics also select items that have the second characteristic, and vice-versa. Two items having characteristics with high affinity for each other are determined to have some similarity to each other, even if very few or no users who selected one of those items ever selected the other of those items. A first item that is determined to be sufficiently similar to second item in this manner may be recommended to a user who has selected the second item as potentially also being of interest to that user.

    摘要翻译: 确定两个项目与每个项目类似,不仅基于以前的实际用户行为,而且还基于所观察到的这两个项目的特征的相关性。 如果选择具有第一特征的项目的高比例的用户也选择具有第二特征的项目,则第一特征和第二特征被确定为彼此具有一些亲和力,反之亦然。 具有彼此具有高亲和力特征的两个项目被确定为彼此具有一些相似性,即使选择了这些项目中的一个的用户很少或没有选择其中一个项目。 可以向已经选择第二项目的用户潜在地也对该用户感兴趣的用户推荐被确定为以这种方式与第二项目充分相似的第一项目。

    System and method for online advertising driven by predicting user interest
    8.
    发明申请
    System and method for online advertising driven by predicting user interest 审中-公开
    通过预测用户兴趣推动在线广告系统和方法

    公开(公告)号:US20090171763A1

    公开(公告)日:2009-07-02

    申请号:US12006179

    申请日:2007-12-31

    IPC分类号: G06Q30/00

    摘要: An improved system and method for online advertising driven by predicting user interest is provided. An advertising demand engine may be provided for selecting advertisements to be served to a user for display with requested content. An advertisement may be correlated to an advertisement previously selected by a user or by other users in the user's segment. An advertising correlation engine may be provided for correlating an advertisement to another advertisement using collaborative filtering, an advertising clustering engine may be provided for clustering correlated advertisements using item-based collaborative filtering, and a user correlation engine may be provided for segmenting users by selected advertisements and creating a cluster of advertisements associated with each cluster of users. Correlated advertisements that are selected may be allocated web page placements and then served to a user for display with requested content.

    摘要翻译: 提供了一种通过预测用户兴趣推动的改进的在线广告系统和方法。 可以提供广告需求引擎用于选择要被提供给用户的广告以便显示所请求的内容。 广告可以与先前由用户或用户区段中的其他用户选择的广告相关联。 可以提供广告相关引擎,用于使用协作过滤将广告与另一广告相关联,可以提供广告聚类引擎用于使用基于项目的协作过滤来聚类相关联的广告,并且可以提供用户相关引擎,用于通过选择的广告来分割用户 以及创建与每个用户群集相关联的广告群集。 所选择的相关广告可以被分配网页展示,然后被提供给用户以显示所请求的内容。

    PREDICTING ITEM-ITEM AFFINITIES BASED ON ITEM FEATURES BY REGRESSION
    9.
    发明申请
    PREDICTING ITEM-ITEM AFFINITIES BASED ON ITEM FEATURES BY REGRESSION 有权
    基于项目功能的预测项目活动

    公开(公告)号:US20110107260A1

    公开(公告)日:2011-05-05

    申请号:US12613503

    申请日:2009-11-05

    IPC分类号: G06F3/048

    CPC分类号: G06Q10/04

    摘要: Two items are determined to be similar to each not only based on previous actual user behavior, but also based on the observed relatedness of the characteristics of those two items. A first characteristic and a second characteristic are determined to have some affinity for each other if a high proportion of users who select items having the first characteristics also select items that have the second characteristic, and vice-versa. Two items having characteristics with high affinity for each other are determined to have some similarity to each other, even if very few or no users who selected one of those items ever selected the other of those items. A first item that is determined to be sufficiently similar to second item in this manner may be recommended to a user who has selected the second item as potentially also being of interest to that user.

    摘要翻译: 确定两个项目与每个项目类似,不仅基于以前的实际用户行为,而且还基于所观察到的这两个项目的特征的相关性。 如果选择具有第一特征的项目的高比例的用户也选择具有第二特征的项目,则第一特征和第二特征被确定为彼此具有一些亲和力,反之亦然。 具有彼此具有高亲和力特征的两个项目被确定为彼此具有一些相似性,即使选择了这些项目中的一个的用户很少或没有选择其中一个项目。 可以向已经选择第二项目的用户潜在地也对该用户感兴趣的用户推荐被确定为以这种方式与第二项目充分相似的第一项目。

    Method and system for performing bi-directional search
    10.
    发明授权
    Method and system for performing bi-directional search 有权
    执行双向搜索的方法和系统

    公开(公告)号:US09323843B2

    公开(公告)日:2016-04-26

    申请号:US12755938

    申请日:2010-04-07

    IPC分类号: G06F17/30

    摘要: When a user enters a primary search query into a primary search query input area to perform a first search of the primary search query, disclosed is a method and system for automatically entering the primary search query into a secondary search query input area to perform a second search of the primary search query. When the user enters a secondary search query into the secondary search query input area to perform a first search of the secondary search query, the method and system automatically enters the secondary search query into the primary search query input area to perform a second search of the secondary search query.

    摘要翻译: 当用户将主搜索查询输入主搜索查询输入区域以执行主搜索查询的第一搜索时,公开了一种用于将主搜索查询自动输入到辅助搜索查询输入区域中以执行第二搜索查询输入区域的方法和系统 搜索主搜索查询。 当用户将辅助搜索查询输入到辅助搜索查询输入区域中以执行辅助搜索查询的第一搜索时,该方法和系统自动将辅助搜索查询输入到主搜索查询输入区域中,以执行第二搜索查询 辅助搜索查询。