Patent · US Active

Data processing to predict affinity for geographical locations

US11468474B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 9, 2017
Grant dateOct 11, 2022
Priority date
Expiry dateJul 12, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.