知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

1166 条记录 (耗时 0.049 秒)

    Systems and methods for prioritizing digital social media posts within a social media interface
    3.
    发明授权
    Systems and methods for prioritizing digital social media posts within a social media interface 有权

    公开(公告)号：US12101383B1

    公开(公告)日：2024-09-24

    申请号：US18148971

    申请日：2022-12-30

    申请人： Meta Platforms, Inc.

    发明人： Yuanrui Gao ,  Padmaneha Tamma Reddy ,  Sen Yang ,  Zihao Zhou ,  Hangcheng Zheng

    IPC分类号： G06F15/173 ,  G06Q50/00 ,  H04L67/50

    CPC分类号： H04L67/535 ,  G06Q50/01

    摘要： The disclosed systems and methods may include (1) identifying social media posts that have been posted to a social media platform by a creator account with fewer than a designated number of followers, (2) creating a social-engagement score for the creator account based on a measure of an amount of digital social engagement generated in response to the social media posts, (3) determining that the social-engagement score surpasses a threshold, (4) in response to (i) the creator account having fewer than the designated number of followers and (ii) the social-engagement score surpassing the threshold, designating the creator account as a prioritized creator account, and (5) presenting, in association with the creator account, a digital visual indicator indicating that the creator account is a prioritized creator account. Various other methods, systems, and computer-readable media are also disclosed.

    SIMILARITY MAPPING OF POST CONTENT IN HYPERSPACE
    5.
    发明公开
    SIMILARITY MAPPING OF POST CONTENT IN HYPERSPACE 审中-公开

    公开(公告)号：US20240303288A1

    公开(公告)日：2024-09-12

    申请号：US18075192

    申请日：2022-12-05

    申请人： Meta Platforms, Inc.

    发明人： Jun Mei ,  Siddarth Reddy Malreddy ,  Piyush Maheshwari ,  Yiqun Liu ,  Kaushik Rangadurai ,  Anthony Robert Bell ,  Fedor Borisyuk ,  Xiaoyi Liu

    IPC分类号： G06F16/9536 ,  G06Q50/00

    CPC分类号： G06F16/9536 ,  G06Q50/01

    摘要： Methods, systems, and storage media for determining the similarities of post content for mapping into a hyperspace. In an exemplary method, the disclosure comprises receiving a query at the processor. The method includes determining post data associated with the query. The post data comprises a plurality of posts provided to a social media platform by various users of the platform. The method includes determining, by the processor, a relationship between at least two posts of the plurality of posts. The method includes training, by the processor, a machine language model. The machine language model is based on the query and the relationship between the at least two posts. The method also generates a hyperspace based on the relationship between the at least two posts and the query.

    SYSTEMS AND METHODS FOR CROSS-APPLICATION SETTINGS CONFIGURATION
    6.
    发明公开
    SYSTEMS AND METHODS FOR CROSS-APPLICATION SETTINGS CONFIGURATION 审中-公开

    公开(公告)号：US20240303097A1

    公开(公告)日：2024-09-12

    申请号：US18179206

    申请日：2023-03-06

    申请人： Meta Platforms, Inc.

    发明人： Marek Matejka

    IPC分类号： G06F9/451 ,  G06F3/0482 ,  G06F3/04847

    CPC分类号： G06F9/453 ,  G06F3/0482 ,  G06F3/04847 ,  G06F16/9538

    摘要： The disclosed systems and methods may include (1) providing, within a digital help center article directed to delineating how to accomplish a digital action within an application, both (i) a description of how to manually accomplish the digital action (including a list of digital steps that, when manually initiated via user input to the application, trigger the digital action to be executed within the application) and (ii) a selectable element configured to trigger the digital action to be executed, bypassing one or more of the digital steps listed in the description, when selected via user input, (2) receiving user input digitally selecting the selectable element within the digital help center article, and (3) in response to receiving the user input digitally selecting the selectable element within the digital help center article, executing the digital action within the application. Various other methods, systems, and computer-readable media are also disclosed.

    Chip-to-chip interconnect with a layered communication architecture
    7.
    发明授权
    Chip-to-chip interconnect with a layered communication architecture 有权

    公开(公告)号：US12061939B2

    公开(公告)日：2024-08-13

    申请号：US17824766

    申请日：2022-05-25

    申请人： Meta Platforms, Inc.

    发明人： Pankaj Kansal ,  Arvind Srinivasan ,  Harikrishna Madadi Reddy ,  Naader Hasani

    IPC分类号： G06F16/23 ,  G06F9/30 ,  G06F9/54

    CPC分类号： G06F9/546 ,  G06F9/3005 ,  G06F9/544

    摘要： A system includes a first integrated circuit package including a first group of one or more artificial intelligence processing units and a first chip-to-chip interconnect communication unit and a second integrated circuit package including a second group of one or more artificial intelligence processing units and a second chip-to-chip interconnect communication unit. The system also includes an interconnect between the first integrated circuit package and the second integrated circuit package, wherein the first chip-to-chip interconnect communication unit and the second chip-to-chip interconnect communication unit manage ethernet-based communication via the interconnect using a layered communication architecture supporting a credit-based data flow control and a retransmission data flow control.

    DIFFERENTIALLY PRIVATE APPROXIMATE DISTINCT-COUNTING SKETCHES
    8.
    发明公开
    DIFFERENTIALLY PRIVATE APPROXIMATE DISTINCT-COUNTING SKETCHES 审中-公开

    公开(公告)号：US20240256530A1

    公开(公告)日：2024-08-01

    申请号：US18104119

    申请日：2023-01-31

    申请人： Meta Platforms, Inc.

    发明人： Jonathan Hehir ,  Graham Cormode ,  Daniel Ting

    IPC分类号： G06F16/242 ,  G06F16/25

    CPC分类号： G06F16/244 ,  G06F16/254

    摘要： A system for determining and merging differentially private approximate distinct-counting sketches is disclosed. A first non-private probabilistic cardinality estimator for a first dataset is determined. The first non-private probabilistic cardinality estimator is converted to a first private probabilistic cardinality estimator for the first dataset with a first noise level. The first private probabilistic cardinality estimator for the first dataset is merged with a second probabilistic cardinality estimator for a second dataset with a second noise level to produce a merged probabilistic cardinality estimator for the first dataset and the second dataset combined together based at least in part on the first noise level and the second noise level. A number of unique elements in the first dataset and the second dataset combined together is estimated based on the merged probabilistic cardinality estimator for the first dataset and the second dataset combined together.