会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 22. 发明授权
    • Mobile device image acquisition using objects of interest recognition
    • 使用感兴趣对象的移动设备图像采集识别
    • US09554030B2
    • 2017-01-24
    • US14500911
    • 2014-09-29
    • Yahoo! Inc.
    • Jia LiHaojian Jin
    • H04N5/232G06K9/32
    • H04N5/23212G06K9/3233H04N5/23216H04N5/23293
    • An approach is provided for acquiring images with camera-enabled mobile devices using objects of interest recognition. A mobile device is configured to acquire an image represented by image data and process the image data to identify a plurality of candidate objects of interest in the image. The plurality of candidate objects of interest may be identified based upon a plurality of low level features or “cues” in the image data. Example cues include, without limitation, color contrast, edge density and superpixel straddling. A particular candidate object of interest is selected from the plurality of candidate objects of interest and a graphical symbol is displayed on a screen of the mobile device to identify the particular candidate object of interest. The particular candidate object of interest may be located anywhere on the image. Passive auto focusing is performed at the location of the particular candidate object of interest.
    • 提供了一种用于使用感兴趣的对象识别摄像机的移动设备来获取图像的方法。 移动装置被配置为获取由图像数据表示的图像并处理图像数据以识别图像中的多个候选对象。 可以基于图像数据中的多个低级特征或“提示”来识别多个候选对象。 示例提示包括但不限于颜色对比度,边缘密度和超像素跨越。 从多个感兴趣的候选对象中选择特定的候选对象,并且在移动设备的屏幕上显示图形符号以识别特定的感兴趣的候选对象。 感兴趣的特定候选对象可以位于图像的任何地方。 在特定候选对象的位置执行被动自动对焦。
    • 24. 发明授权
    • Methods and systems for ranking items on a presentation area based on binary outcomes
    • 基于二进制结果对呈现区域上的项目进行排序的方法和系统
    • US09529858B2
    • 2016-12-27
    • US14199729
    • 2014-03-06
    • Yahoo! Inc.
    • Asad ShethFerras Hamad
    • G06F17/30
    • G06F17/3053G06F17/3005G06F17/30905
    • A method includes accessing a number of cards from a database. The cards are ranked in the database based on a test conducted on a number of users. The cards are associated with one or more rule states. The one or more rule states provide binary outcomes of one or more rules. Each rule is identified using a code. The test is conducted by presenting different random sequences of the cards to different users and receiving inputs from the number of users. The method further includes receiving a request for a presentation area from a client device operated by a user. The presentation area is used for displaying the number of cards in an order, which is determined based on the test. The method includes providing the number of cards for display in the order within the presentation area on the client device of the user in response to the request.
    • 一种方法包括从数据库访问多个卡。 基于对许多用户进行的测试,这些卡在数据库中排名。 这些卡与一个或多个规则状态相关联。 一个或多个规则状态提供一个或多个规则的二进制结果。 每个规则都使用代码来标识。 通过向不同的用户呈现不同的随机序列并从用户数量接收输入来进行测试。 该方法还包括从用户操作的客户端设备接收对于呈现区域的请求。 显示区域用于显示按照测试确定的顺序的卡片数量。 该方法包括响应于该请求,在用户的客户端设备上以呈现区域内的顺序提供用于显示的卡片数量。
    • 26. 发明申请
    • SYSTEMS AND METHODS FOR ONLINE CONTENT RECOMMENDATION
    • 用于在线内容推荐的系统和方法
    • US20160371589A1
    • 2016-12-22
    • US14748333
    • 2015-06-24
    • Yahoo! Inc.
    • Nadav GOLBANDIChao Wang
    • G06N5/04G06N7/00G06N99/00
    • G06N20/00G06F16/9535G06Q30/0241G06Q30/0269
    • The present disclosure relates to computer systems implementing methods for online content recommendation. The computer systems may be configured to receive a training sample from a first client device corresponding to a predefined feedback interacting with online content displayed on the first client device; update a preexisting training database in real-time based on the received training sample to generate an updated training sample, wherein prior to being updated based on the training sample received from the first client, the training database includes a set of historical training samples; conduct a regression training to a computer learning model in real-time, using the updated training sample, to produce a set of trained parameters for an online content recommendation model; call the set of trained parameters in real-time to determine recommend online content for a second user with the online content recommendation model; and send the recommended online content to a second client device of the second user.
    • 本公开涉及实现在线内容推荐方法的计算机系统。 计算机系统可以被配置为从第一客户端设备接收对应于与在第一客户端设备上显示的在线内容交互的预定义反馈的训练样本; 基于所接收的训练样本来实时更新预先存在的训练数据库以生成更新的训练样本,其中在根据从第一客户端接收到的训练样本进行更新之前,训练数据库包括一组历史训练样本; 对计算机学习模型实时进行回归训练,使用更新的训练样本,为在线内容推荐模型生成一组经过训练的参数; 通过在线内容推荐模型实时调用一组受过训练的参数,以确定第二个用户的推荐在线内容; 并将推荐的在线内容发送给第二个用户的第二个客户端设备。
    • 29. 发明授权
    • Summarization of media object collections
    • 媒体对象集合的总结
    • US09507778B2
    • 2016-11-29
    • US11437344
    • 2006-05-19
    • Alexander B. JaffeMor NaamanMarc E. Davis
    • Alexander B. JaffeMor NaamanMarc E. Davis
    • G06F17/30G06K9/00G06K9/62G11B27/10
    • G06F17/30041G06F17/3005G06F17/30064G06F17/30241G06K9/00664G06K9/6219G11B27/105
    • In one example, an apparatus and method are provided for summarizing (or selecting a representative subset from) a collection of media objects. A method includes selecting a subset of media objects from a collection of geographically-referenced (e.g., via GPS coordinates) media objects based on a pattern of the media objects within a spatial region. The media objects may further be selected based on (or be biased by) various social aspects, temporal aspects, spatial aspects, or combinations thereof relating to the media objects and/or a user. Another method includes clustering a collection of media objects in a cluster structure having a plurality of subclusters, ranking the media objects of the plurality of subclusters, and selection logic for selecting a subset of the media objects based on the ranking of the media objects.
    • 在一个示例中,提供了用于从媒体对象的集合中总结(或选择代表性子集)的装置和方法。 一种方法包括基于空间区域内的媒体对象的图案,从地理参考的集合(例如,经由GPS坐标)媒体对象中选择媒体对象的子集。 媒体对象还可以基于与媒体对象和/或用户有关的各种社会方面,时间方面,空间方面或其组合(或偏向于)来进行选择。 另一种方法包括在具有多个子集群的集群结构中聚集媒体对象的集合,对多个子集群中的媒体对象进行排序,以及基于媒体对象的排名来选择媒体对象的子集的选择逻辑。