- 专利标题: Data processing to predict affinity for geographical locations
-
申请号: US15808756申请日: 2017-11-09
-
公开(公告)号: US11468474B2公开(公告)日: 2022-10-11
- 发明人: Arpit Sood , Gurpreetsingh Baljeetsingh Sachdev , Alex Meyer , Rohit Poddar , Manisha Singh , Tao Cui Baecklund , Anthony Mang Yau , Shashikant Khandelwal
- 申请人: Meta Platforms, Inc.
- 申请人地址: US CA Menlo Park
- 专利权人: Meta Platforms, Inc.
- 当前专利权人: Meta Platforms, Inc.
- 当前专利权人地址: US CA Menlo Park
- 代理机构: Fenwick & West LLP
- 主分类号: G06Q30/02
- IPC分类号: G06Q30/02 ; G06Q50/00 ; G06Q10/06 ; G06N5/02
摘要:
An online system uses a model to determine affinities of users for geographical locations. Using the affinities, which may indicate travel-related preferences of the users, the online system may customize content items to include content captured by client devices of other users of the online system. For example, the online system presents to a particular user a content item including a photo or video of a geographical location captured by a camera of a client device of another user who is connected to the particular user. The model may implement, for example, collaborative filtering or other machine learning techniques to determine commonalities between users' travel affinities. Additionally, the model may determine latent properties or temporal trends of user preferences based on training data including historical actions performed on the online system or social data. The model may also classify different types of geographical locations.
公开/授权文献
信息查询