一种直播间排序方法、电子设备及可读存储介质

    公开(公告)号:WO2019134290A1

    公开(公告)日:2019-07-11

    申请号:PCT/CN2018/082352

    申请日:2018-04-09

    CPC classification number: H04N21/251 H04N21/25891 H04N21/4667 H04N21/4756

    Abstract: 本发明提供了一种直播间排序方法、电子设备及可读存储介质,用于提供一种能够反映直播间的质量和成长潜力的有效的排序方式,以确保直播间的展示顺序的公正性与合理性。该排序方法包括:在直播应用程序开启情况下,确定当前正在直播的直播间;基于在历史时间范围内所述当前正在直播的直播间中每个直播间的历史观看记录、历史新增关注记录与历史取消关注记录,对每个直播间进行评分,获得所述当前正在直播的直播间中每个直播间的评分值;按评分值由高至低的顺序对当前正在直播的直播间进行排序,以使得客户端按评分值由高至低的顺序依次展示当前正在直播的直播间。

    一种推荐方法、装置及计算机设备

    公开(公告)号:WO2019095614A1

    公开(公告)日:2019-05-23

    申请号:PCT/CN2018/082182

    申请日:2018-04-08

    Abstract: 本发明实施例提供了一种推荐方法、装置及计算机设备,所述方法包括:获取用户在预设时刻t之前的时间段内观看直播间i的第一总次数,及进入直播间i所属直播分区s的第二总次数;获取用户在所述时刻t之前最后一次观看直播间i的第一时刻,及在时刻t之前的最后一次观看直播分区s中任意直播间的第二时刻;获取所述用户在时刻t之前的时间段内,在直播平台中观看所有带有直播标签的各直播间的第三总次数;及在时刻t之前,在直播平台中最后一次观看带有直播标签的任意直播间的第三时刻;基于第一总次数、第二总次数、第一时刻、第二时刻、第三总次数及第三时刻确定用户在所述时刻t对直播间i的惊喜值。

    METHODS AND SYSTEMS OF SPATIOTEMPORAL PATTERN RECOGNITION FOR VIDEO CONTENT DEVELOPMENT
    5.
    发明申请
    METHODS AND SYSTEMS OF SPATIOTEMPORAL PATTERN RECOGNITION FOR VIDEO CONTENT DEVELOPMENT 审中-公开
    视频内容开发的时空模式识别方法和系统

    公开(公告)号:WO2018053257A1

    公开(公告)日:2018-03-22

    申请号:PCT/US2017/051768

    申请日:2017-09-15

    Abstract: Providing enhanced video content includes processing at least one video feed through at least one spatiotemporal pattern recognition algorithm that uses machine learning to develop an understanding of a plurality of events and to determine at least one event type for each of the plurality of events. The event type includes an entry in a relationship library detailing a relationship between two visible features. Extracting and indexing a plurality of video cuts from the video feed is performed based on the at least one event type determined by the understanding that corresponds to an event in the plurality of events detectable in the video cuts. Lastly, automatically and under computer control, an enhanced video content data structure is generated using the extracted plurality of video cuts based on the indexing of the extracted plurality of video cuts.

    Abstract translation: 提供增强的视频内容包括通过至少一个时空模式识别算法来处理至少一个视频馈送,该时间模式识别算法使用机器学习来开发对多个事件的理解并确定每个事件的至少一个事件类型 在多个事件中。 事件类型在关系库中包含一个条目,详细说明两个可见特征之间的关系。 从视频馈送中提取和索引多个视频剪辑是基于由对应于视频剪辑中可检测的多个事件中的事件的理解所确定的至少一个事件类型来执行的。 最后,自动且在计算机控制下,基于提取的多个视频剪辑的索引,使用所提取的多个视频剪辑来生成增强视频内容数据结构。

    A SYSTEM AND METHOD FOR RECORDING AND DISPLAYING A REACTION TO A FOCUS
    7.
    发明申请
    A SYSTEM AND METHOD FOR RECORDING AND DISPLAYING A REACTION TO A FOCUS 审中-公开
    记录和显示对焦点反应的系统和方法

    公开(公告)号:WO2017083875A1

    公开(公告)日:2017-05-18

    申请号:PCT/US2016/061936

    申请日:2016-11-14

    Inventor: AREND, Steve

    CPC classification number: H04N21/44218 H04N7/147 H04N21/251 H04N21/6582

    Abstract: The present invention relates to a system and method for recording and displaying a reaction to a focus in a professional setting, an education setting, and a personal setting. A reaction stream includes instances of reaction data, wherein each of the instances of reaction data includes a user sentiment and a focus point, and wherein the focus point identifies a portion of a session to which the user sentiment is directed. The system may include a plurality of user devices, a supervisor device, and/or a server.

    Abstract translation: 本发明涉及用于在专业设置,教育设置和个人设置中记录和显示对焦点的反应的系统和方法。 反应流包括反应数据的实例,其中反应数据的每个实例包括用户情绪和焦点,并且其中焦点标识用户情绪指向的会话的一部分。 该系统可以包括多个用户设备,管理设备和/或服务器。

    SUPPORT OF CROWDSOURCED VIDEO
    8.
    发明申请
    SUPPORT OF CROWDSOURCED VIDEO 审中-公开
    支持人群视频

    公开(公告)号:WO2017080701A1

    公开(公告)日:2017-05-18

    申请号:PCT/EP2016/071479

    申请日:2016-09-13

    CPC classification number: H04N21/27 H04N21/234 H04N21/251 H04N21/2665

    Abstract: Various networks on which media clips are shared may benefit from appropriate handling of shared media. For example, systems involving video sharing may benefit from methods and devices that support crowdsourced video. A method can include receiving a multimedia element. The method can also include storing the multimedia element as reference content. The method can further include receiving a recording related to the reference content. The method can additionally include storing the recording and a relation between the recording and the reference content. The relationship can include a video-editing relationship to the reference content. The method can also include providing the video-editing relationship upon receiving selection information indicative of at least one of the recording or the reference content.

    Abstract translation: 共享媒体剪辑的各种网络可以受益于对共享媒体的适当处理。 例如,涉及视频共享的系统可能受益于支持众包视频的方法和设备。 一种方法可以包括接收多媒体元素。 该方法还可以包括将多媒体元素存储为参考内容。 该方法可以进一步包括接收与参考内容有关的记录。 该方法可以另外包括存储记录和记录与参考内容之间的关系。 该关系可以包括与参考内容的视频编辑关系。 该方法还可以包括在接收到指示记录或参考内容中的至少一个的选择信息时提供视频编辑关系。

    SYSTEM FOR ENABLING A VIRTUAL THEATER
    9.
    发明申请
    SYSTEM FOR ENABLING A VIRTUAL THEATER 审中-公开
    启用虚拟剧场的系统

    公开(公告)号:WO2017003530A1

    公开(公告)日:2017-01-05

    申请号:PCT/US2016/024100

    申请日:2016-03-24

    Abstract: The disclosed virtual theater system includes capture devices for capturing video and audio of a live even and converting the video and audio into a data stream. The system also includes a production center for receiving the data stream and compressing the data stream to generate a compressed data stream, for determining the number of one or more viewing devices subscribed or reserved to view the live event, and for determining data bandwidth consumption characteristics of the one or more viewing devices. Also included is a server for receiving the compressed data stream, the number of one or more viewing devices, and the data bandwidth consumption characteristics from the production center over a network. The server also duplicates and divides the compressed data stream out to the one or more viewing devices depending on the number of viewing devices subscribed or reserved (cyberseats reserved) to view the live event.

    Abstract translation: 所公开的虚拟影院系统包括用于捕获实时均匀的视频和音频并将视频和音频转换成数据流的捕获装置。 该系统还包括用于接收数据流并压缩数据流以生成压缩数据流的生产中心,用于确定订阅或保留以查看实时事件的一个或多个观看设备的数量,以及用于确定数据带宽消耗特性 的一个或多个观看设备。 还包括用于从生产中心通过网络接收压缩数据流,一个或多个观看设备的数量和数据带宽消耗特性的服务器。 服务器还根据订阅或预留的观看设备的数量(网络保留)来复制并分解压缩的数据流到一个或多个观看设备以查看实时事件。

Patent Agency Ranking