RECOMMENDATIONS UTILIZING META-DATA BASED PAIR-WISE LIFT PREDICTIONS
    1.
    发明申请
    RECOMMENDATIONS UTILIZING META-DATA BASED PAIR-WISE LIFT PREDICTIONS 审中-公开
    推荐使用基于元数据的配对提升预测

    公开(公告)号:US20080097821A1

    公开(公告)日:2008-04-24

    申请号:US11552467

    申请日:2006-10-24

    IPC分类号: G07G1/00

    CPC分类号: G06Q30/02 G06Q30/0201

    摘要: The subject disclosure pertains to systems and methods for facilitating generation of item recommendations based at least in part upon pair-wise lift. Pair-wise lift is a measure of correlation between a pair of items and is generally calculated based upon past usage data. If usage data is insufficient or unavailable, pair-wise lift for a pair of items can be estimated based upon metadata associated with the items. In other aspects, pair-wise lift can be used to generate an explanation for recommended items. An explanation for an item recommendation can be based upon common metadata features associated with the item pair. The relative impact each metadata feature has on predicted pair-wise lift can be evaluated to determine the common feature(s) most likely to have caused the item to be recommended.

    摘要翻译: 本发明涉及用于至少部分地基于成对提升来促进产生项目建议的系统和方法。 成对升降是一对物品之间的相关性的度量,并且通常基于过去的使用数据计算。 如果使用数据不足或不可用,则可以基于与项目相关联的元数据来估计一对项目的成对提升。 在其他方面,可以使用成对提升来产生推荐项目的说明。 项目建议的解释可以基于与项目对相关联的公共元数据特征。 可以评估每个元数据特征对预测的成对提升的相对影响,以确定最可能导致该项目被推荐的共同特征。

    VIRTUAL WORLD PLATFORM GAMES CONSTRUCTED FROM DIGITAL IMAGERY
    3.
    发明申请
    VIRTUAL WORLD PLATFORM GAMES CONSTRUCTED FROM DIGITAL IMAGERY 审中-公开
    虚拟世界平台游戏由数字图像构建

    公开(公告)号:US20090186694A1

    公开(公告)日:2009-07-23

    申请号:US12015556

    申请日:2008-01-17

    IPC分类号: A63F13/00

    摘要: An interactive game within a virtual world platform is provided wherein a sender can hide an object within a mapping application. An intended recipient of the object can be notified that the object is available and a clue can be provided. The clue can direct the recipient in searching for where the object is hidden. The objects can be intended for a single recipient, multiple recipients, or open to everyone on a first-come-first-served basis. The objects can be stolen by others and/or the objects can be re-gifted after being found. After being found, the virtual object can be automatically or manually converted into a non-virtual object.

    摘要翻译: 提供了虚拟世界平台内的交互式游戏,其中发送者可以隐藏映射应用内的对象。 可以通知该对象的预期接收者该对象是可用的,并且可以提供线索。 线索可以指示收件人搜索隐藏对象的位置。 这些对象可以用于单个收件人,多个收件人,也可以先到先得的方式向所有人开放。 这些物体可以被其他人偷走,和/或物体被发现之后可以重新进行。 找到后,可以将虚拟对象自动或手动转换为非虚拟对象。

    Quality based pricing and ranking for online ads
    4.
    发明授权
    Quality based pricing and ranking for online ads 有权
    基于质量的定价和在线广告的排名

    公开(公告)号:US08527339B2

    公开(公告)日:2013-09-03

    申请号:US12146473

    申请日:2008-06-26

    IPC分类号: G06Q99/00

    CPC分类号: G06Q30/02 G06Q30/0243

    摘要: A “Quality-Based Ad Pricer” prices ads as a function of how users respond to a particular page and/or domain to which they are sent by an online advertisement. User experience is improved by ensuring that advertisements that are more relevant to a user are priced less than an ads which are less relevant to the user. In particular, a quality factor for each ad is determined as a property of the advertiser's site based on measured user behaviors with respect to that site. This quality factor is then used in ranking, selecting, and pricing ads in an automated online auction. Further, while ad aggregators are not excluded from the ad market by the pricing rules of the Quality-Based Ad Pricer, these rules ensure that there is a “level playing field” such that ads of merchants are not excluded by the ads of ad aggregators.

    摘要翻译: “质量为基础的广告价格”将广告定价为用户如何响应通过在线广告发送的特定页面和/或域的功能。 通过确保与用户更相关的广告的价格低于与用户相关性较低的广告来提高用户体验。 特别地,基于相对于该站点的测量用户行为,每个广告的品质因子被确定为广告商网站的属性。 然后,此质量因子用于在自动化在线拍卖中对广告进行排名,选择和定价。 此外,虽然广告集合商并未按照质量为基础的广告价格定价规则从广告市场中排除,但这些规则确保有一个“公平竞争的环境”,广告商广告不会被广告集合商的广告排除在外 。

    PREDICTIVE INTERFACES WITH USABILITY CONSTRAINTS
    5.
    发明申请
    PREDICTIVE INTERFACES WITH USABILITY CONSTRAINTS 审中-公开
    具有可用性约束的预测接口

    公开(公告)号:US20100315266A1

    公开(公告)日:2010-12-16

    申请号:US12484532

    申请日:2009-06-15

    IPC分类号: H03K17/94

    CPC分类号: G06F3/0237 G06F3/04886

    摘要: A “Constrained Predictive Interface” uses predictive constraints to improve accuracy in user interfaces such as soft keyboards, pen interfaces, multi-touch interfaces, 3D gesture interfaces, EMG based interfaces, etc. In various embodiments, the Constrained Predictive Interface allows users to take any desired action at any time by taking into account a likelihood of possible user actions in different contexts to determine intended user actions. For example, to enable a virtual keyboard interface, various embodiments of the Constrained Predictive Interface provide key “sweet spots” as predictive constraints that allow the user to select particular keys regardless of any probability associated with the selected or neighboring keys. In further embodiments, the Constrained Predictive Interface provides hit target resizing via various piecewise constant touch models in combination with various predictive constraints. In general, hit target resizing provides dynamic real-time virtual resizing of one or more particular keys based on various probabilistic criteria.

    摘要翻译: “约束预测接口”使用预测约束来提高诸如软键盘,笔接口,多点触摸界面,3D手势接口,基于EMG的接口等用户界面的准确性。在各种实施例中,约束预测接口允许用户采取 通过考虑在不同上下文中可能的用户动作的可能性来确定预期的用户动作,在任何时候执行任何期望的动作。 例如,为了启用虚拟键盘接口,约束预测接口的各种实施例提供关键的“甜点”作为预测约束,其允许用户选择特定的密钥,而不管与所选择的或相邻的密钥相关联的任何概率如何。 在另外的实施例中,约束预测接口通过各种分段常数触摸模型结合各种预测约束提供命中目标调整大小。 一般来说,命中目标调整大小基于各种概率标准提供一个或多个特定键的动态实时虚拟调整大小。

    Training random walks over absorbing graphs
    6.
    发明授权
    Training random walks over absorbing graphs 有权
    训练随机走过吸收图

    公开(公告)号:US07778945B2

    公开(公告)日:2010-08-17

    申请号:US11768867

    申请日:2007-06-26

    IPC分类号: G06F15/18

    CPC分类号: G06Q10/04 G06Q30/0283

    摘要: A random walk is performed over a graph, such as an augmented bipartite graph, relating to ownership data with respect to a plurality of users and items owned; the graph can provide social links between the users as well. Items can be recommended to users who do not own the items by randomly walking the graph starting at the user node to which the recommendation will be given. The random walk can step from user to user or from user to item; when an item is reached, the node can be absorbing such that the random walk terminates. The arrived item is recommended to the user. Parameters can also be provided to affect decisions made during the walk about which users to walk to and/or whether to walk to a user or an item.

    摘要翻译: 在与多个用户和所拥有的项目相关的所有权数据相关的图形上执行随机游走,例如增强的二分图; 该图也可以提供用户之间的社交联系。 可以通过随机地从图中给出推荐的用户节点开始,图形推荐给不拥有项目的用户。 随机步行可以从用户到用户或从用户到项目步进; 当达到项目时,节点可以被吸收,使得随机游走终止。 推荐给用户的到达项目。 还可以提供参数来影响在步行期间作出的决定,哪些用户要走到哪里,和/或是否走到用户或物品。

    QUALITY BASED PRICING AND RANKING FOR ONLINE ADS
    7.
    发明申请
    QUALITY BASED PRICING AND RANKING FOR ONLINE ADS 有权
    基于质量的定价和排名在线ADS

    公开(公告)号:US20090327032A1

    公开(公告)日:2009-12-31

    申请号:US12146473

    申请日:2008-06-26

    IPC分类号: G06Q30/00 G06Q10/00

    CPC分类号: G06Q30/02 G06Q30/0243

    摘要: A “Quality-Based Ad Pricer” prices ads as a function of how users respond to a particular page and/or domain to which they are sent by an online advertisement. User experience is improved by ensuring that advertisements that are more relevant to a user are priced less than an ads which are less relevant to the user. In particular, a quality factor for each ad is determined as a property of the advertiser's site based on measured user behaviors with respect to that site. This quality factor is then used in ranking, selecting, and pricing ads in an automated online auction. Further, while ad aggregators are not excluded from the ad market by the pricing rules of the Quality-Based Ad Pricer, these rules ensure that there is a “level playing field” such that ads of merchants are not excluded by the ads of ad aggregators.

    摘要翻译: “质量为基础的广告价格”将广告定价为用户如何响应通过在线广告发送的特定页面和/或域的功能。 通过确保与用户更相关的广告的价格低于与用户相关性较低的广告来提高用户体验。 特别地,基于相对于该站点的测量用户行为,每个广告的品质因子被确定为广告商网站的属性。 然后,此质量因子用于在自动在线拍卖中对广告进行排名,选择和定价。 此外,虽然广告集合商并未按照质量为基础的广告价格定价规则从广告市场中排除,但这些规则确保有一个“公平竞争的环境”,广告商广告不会被广告集合商的广告排除在外 。

    TRAINING RANDOM WALKS OVER ABSORBING GRAPHS
    9.
    发明申请
    TRAINING RANDOM WALKS OVER ABSORBING GRAPHS 有权
    在吸收格局上训练随机的沃尔克

    公开(公告)号:US20090006290A1

    公开(公告)日:2009-01-01

    申请号:US11768867

    申请日:2007-06-26

    CPC分类号: G06Q10/04 G06Q30/0283

    摘要: A random walk is performed over a graph, such as an augmented bipartite graph, relating to ownership data with respect to a plurality of users and items owned; the graph can provide social links between the users as well. Items can be recommended to users who do not own the items by randomly walking the graph starting at the user node to which the recommendation will be given. The random walk can step from user to user or from user to item; when an item is reached, the node can be absorbing such that the random walk terminates. The arrived item is recommended to the user. Parameters can also be provided to affect decisions made during the walk about which users to walk to and/or whether to walk to a user or an item.

    摘要翻译: 在与多个用户和所拥有的项目相关的所有权数据相关的图形上执行随机游走,例如增强的二分图; 该图也可以提供用户之间的社交联系。 可以通过随机地从图中给出推荐的用户节点开始,图形推荐给不拥有项目的用户。 随机步行可以从用户到用户或从用户到项目步进; 当达到项目时,节点可以被吸收,使得随机游走终止。 推荐给用户的到达项目。 还可以提供参数来影响在步行期间作出的决定,哪些用户要步行到和/或是否走到用户或物品。