中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

29 records (took 0.016 seconds)

    COLLABORATIVE FILTERING IN DIRECTED GRAPH
    2.
    发明申请
    COLLABORATIVE FILTERING IN DIRECTED GRAPH 审中-公开
    方向图中的协同过滤

    公开(公告)号：US20160342899A1

    公开(公告)日：2016-11-24

    申请号：US14718391

    申请日：2015-05-21

    Applicant: Facebook, Inc.

    Inventor： Maja Kabiljo ,  Aleksandar Ilic

    IPC: G06N5/04 ,  G06N7/00 ,  H04L29/08

    CPC classification number: H04L67/22 ,  G06N5/003 ,  G06N99/005 ,  G06Q50/01

    Abstract: Embodiments are disclosed for data computation of collaborative filtering in a social network. Collaborative filtering involves predicting a user's behavior or interests based on other users' behavior or interests. To predict a user's interests in an item such as a picture, a system performs an iterative computation to perform an evaluation by solving an objective function. The system characterizes “users” as “vertices” in a directed graph, “relationship among users” as “edges” in the directed graph, and “items” as “worker data” that is locally-calculated, stored, and managed in individual worker computers. When a local computing process is completed, the “worker data” can be transferred to other worker computers so as to complete a whole computing process. The system enhances an overall computing efficiency and enables collaborative filtering across a large data set.

    Abstract translation: 公开了用于社交网络中协作过滤的数据计算的实施例。 协作过滤涉及基于其他用户的行为或兴趣来预测用户的行为或兴趣。 为了预测用户在诸如图片的项目中的兴趣，系统执行迭代计算以通过求解目标函数来执行评估。 该系统将有向图中的“用户”表示为“顶点”，将有向图中的“用户之间的关系”设为“边缘”，将个体作为“个人数据”作为“个体”进行本地计算，存储和管理的“工作者数据” 工作电脑。 当本地计算过程完成时，可以将“工作人员数据”传输到其他工作计算机，以完成整个计算过程。 该系统增强了整体计算效率，并实现了跨大数据集的协同过滤。

    Check-in Suggestions
    3.
    发明申请
    Check-in Suggestions 审中-公开
    入住建议

    公开(公告)号：US20160147756A1

    公开(公告)日：2016-05-26

    申请号：US14551202

    申请日：2014-11-24

    Applicant: Facebook, Inc.

    Inventor： Kia Dalili ,  Jan Kalis ,  Aleksandar Ilic

    IPC: G06F17/30

    CPC classification number: G06F16/9535 ,  G06Q30/0241 ,  G06Q50/01

    Abstract: In one embodiment, a method includes receiving first-user input corresponding to a check-in for the first user, accessing a check-in history of the first user, and identifying one or more second users based at least in part on the check-in history, where the first user is a user of a social-networking system that includes a number of nodes and a number of edges connecting the nodes, with at least one node corresponding to the first user. The method includes providing an identification of one or more of the identified second users for display to the first user in association with the check-in.

    Abstract translation: 在一个实施例中，一种方法包括：接收与第一用户的签到相对应的第一用户输入，访问第一用户的登记历史，以及至少部分地基于所述检查来识别一个或多个第二用户， 在历史上，第一用户是社交网络系统的用户，其包括连接节点的多个节点和多个边缘与至少一个对应于第一用户的节点。 该方法包括提供一个或多个所识别的第二用户的标识，以便与登记相关联地向第一用户显示。

    ELECTRONIC NOTIFICATIONS
    8.
    发明申请
    ELECTRONIC NOTIFICATIONS 有权
    电子通知

    公开(公告)号：US20160036887A1

    公开(公告)日：2016-02-04

    申请号：US14450820

    申请日：2014-08-04

    Applicant: Facebook, Inc.

    Inventor： Aleksandar Ilic ,  Florin Ratiu ,  John Torres Fremlin ,  David S. Park ,  Matthew William Kelly

    IPC: H04L29/08 ,  H04L12/58

    CPC classification number: H04L67/26 ,  H04L51/32 ,  H04L67/02 ,  H04L67/10 ,  H04L67/22 ,  H04L67/306

    Abstract: In one embodiment, a method includes accessing for a user one or more electronic notifications that include information about a social network. The social network includes a plurality of nodes connected by a plurality of edges, with at least one node corresponding to the user. The method further includes determining, for each of the electronic notifications, a score that estimates whether a user interaction with the social network will result if the electronic notification is provided to the user. The method further includes determining, based at least in part on the determined scores, an action to take with respect to the electronic notifications.

    Abstract translation: 在一个实施例中，一种方法包括访问用户包括关于社交网络的信息的一个或多个电子通知。 社交网络包括通过多个边缘连接的多个节点，其中至少一个节点对应于用户。 该方法还包括为每个电子通知确定评估如果向用户提供电子通知，是否会导致用户与社交网络的交互的分数。 该方法还包括至少部分地基于所确定的分数来确定关于电子通知所采取的动作。

    Collaborative filtering in directed graph
    9.
    发明授权
    Collaborative filtering in directed graph 有权

    公开(公告)号：US10313457B2

    公开(公告)日：2019-06-04

    申请号：US14718391

    申请日：2015-05-21

    Applicant: Facebook, Inc.

    Inventor： Maja Kabiljo ,  Aleksandar Ilic

    IPC: G06N5/00 ,  H04L29/08 ,  G06Q50/00 ,  G06N20/00

    Abstract: Embodiments are disclosed for data computation of collaborative filtering in a social network. Collaborative filtering involves predicting a user's behavior or interests based on other users' behavior or interests. To predict a user's interests in an item such as a picture, a system performs an iterative computation to perform an evaluation by solving an objective function. The system characterizes “users” as “vertices” in a directed graph, “relationship among users” as “edges” in the directed graph, and “items” as “worker data” that is locally-calculated, stored, and managed in individual worker computers. When a local computing process is completed, the “worker data” can be transferred to other worker computers so as to complete a whole computing process. The system enhances an overall computing efficiency and enables collaborative filtering across a large data set.

    Evaluating feature vectors across disjoint subsets of decision trees
    10.
    发明授权
    Evaluating feature vectors across disjoint subsets of decision trees 有权

    公开(公告)号：US10217052B2

    公开(公告)日：2019-02-26

    申请号：US14699657

    申请日：2015-04-29

    Applicant: Facebook, Inc.

    Inventor： Oleksandr Kuvshynov ,  Aleksandar Ilic

    IPC: G06N5/02 ,  G06K9/00 ,  G06N99/00

    Abstract: The disclosure is directed to evaluating feature vectors using decision trees. Typically, the number of feature vectors and the number of decision trees are very high, which prevents loading them into a processor cache. The feature vectors are evaluated by processing the feature vectors across a disjoint subset of trees repeatedly. After loading the feature vectors into the cache, they are evaluated across a first subset of trees, then across a second subset of trees and so on. If the values based on the first and second subsets satisfy a specified criterion, further evaluation of the feature vectors across the remaining of the decision trees is terminated, thereby minimizing the number of trees evaluated and therefore, consumption of computing resources.

Patent Agency Ranking