公开(公告)号：US08756239B2

公开(公告)日：2014-06-17

申请号：US13866095

申请日：2013-04-19

Applicant: c/o Facebook, Inc.

Inventor： Akhil Wable ,  Hong Yan ,  Spencer G. Ahrens ,  Yofay Kari Lee ,  Guizhen Yang

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30321 ,  G06F17/30486 ,  G06F17/30551 ,  G06F17/30628 ,  G06F17/30631 ,  G06F17/30864 ,  G06F17/3087 ,  G06F17/30958 ,  G06Q30/02

Abstract: Indexing and retrieving real time content in a social networking system is disclosed. A user-term index includes user-term partitions, each user-term partition comprising temporal databases. As a post is received from a user, a user identifier, a post identifier, and a post is extracted. An object store communicatively coupled to a temporal database for recently received content is queried to determine whether terms in the post has already been stored. A term identifier is stored in the user-term index with the user and post identifiers. A forward index stores the post by post identifier. Responsive to a search query, the user-term index is searched by the user's connections and the terms. A real time search engine compiles the results of the user-term index query and retrieves the stored posts from the forward index. The search results may then be ranked and cached before presentation to the searching user.

Abstract translation: 公开了在社交网络系统中索引和检索实时内容。 用户术语索引包括用户术语分区，每个用户术语分区包括时间数据库。 当从用户接收到帖子时，提取用户标识符，帖子标识符和帖子。 查询通信地耦合到最近接收的内容的时间数据库的对象存储库，以确定该帖子中的术语是否已被存储。 术语标识符与用户和职位标识符一起存储在用户术语索引中。 转发索引以邮件标识符存储帖子。 响应于搜索查询，用户术语索引由用户的连接和术语搜索。 实时搜索引擎编译用户术语索引查询的结果，并从前向索引检索存储的帖子。 然后可以在向搜索用户呈现之前对搜索结果进行排序和缓存。

公开(公告)号：US20140156745A1

公开(公告)日：2014-06-05

申请号：US13690338

申请日：2012-11-30

Applicant: Facebook, Inc.

Inventor： Ming Hua ,  Hong Yan

IPC: G06F15/16

CPC classification number: H04L67/1095 ,  H04L67/1029 ,  H04L67/1034 ,  H04L67/306 ,  H04L69/40

Abstract: Online systems store information describing a large number of users in order to process requests accessing the user information. The user information is distributed across multiple servers. The distribution is performed so that the information is available even if one or more servers fail. The user information is distributed across a first set of servers and a second copy of the user information is distributed across a second set of servers. The user information from each server of the first set is uniformly distributed across multiple servers from the second set, for example, using random distribution, round robin strategy, or any other strategy that uniformly distributes the information across a given set of processors. Requests previously directed to a failed server are redistributed across multiple servers thereby load balancing the processing of these requests.

Abstract translation: 在线系统存储描述大量用户的信息，以处理访问用户信息的请求。 用户信息分布在多个服务器上。 执行分发，使得即使一个或多个服务器发生故障，信息也可用。 用户信息分布在第一组服务器上，并且用户信息的第二副本分布在第二组服务器上。 来自第一组的每个服务器的用户信息均匀地分布在来自第二组的多个服务器上，例如使用随机分布，循环策略或在给定的一组处理器上均匀分布信息的任何其他策略。 以前指向故障服务器的请求将跨多个服务器重新分配，从而负载平衡这些请求的处理。

公开(公告)号：US20140156566A1

公开(公告)日：2014-06-05

申请号：US13689969

申请日：2012-11-30

Applicant: Facebook, Inc.

Inventor： Igor Kabiljo ,  Aleksandar Ilic ,  Ming Hua ,  Hong Yan

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06Q30/02 ,  G06Q50/01

Abstract: Online systems generate predictors for predicting actions of users of the online system. The online system receives requests to generate predictor models for predicting whether a user is likely to take an action of a particular action type. The request specifies the type of action and criteria for identifying a successful instance of the action type and a failure instance of the action type. The online system collects data including successful and failure instances of the action type. The online system generates one or more predictors of different types using the generated data. The online system evaluates and compares the performance of the different predictors generated and selects a predictor based on the performance. The online system returns a handle to access the generated predictor to the requester of the predictor.

Abstract translation: 在线系统生成用于预测在线系统用户的动作的预测因子。 在线系统接收生成用于预测用户是否可能采取特定动作类型的动作的预测器模型的请求。 请求指定用于标识操作类型的成功实例的动作类型和标准，以及动作类型的失败实例。 在线系统收集数据，包括操作类型的成功和失败实例。 在线系统使用生成的数据生成不同类型的一个或多个预测变量。 在线系统评估并比较生成的不同预测变量的性能，并根据性能选择预测变量。 在线系统返回一个句柄来访问生成的预测变量到预测变量的请求者。