US 12,443,630 B1
Displaying an interactive geographical map of sources
Benjamin Knight, Oakland, CA (US); Samuel K. Sherman, Seattle, WA (US); Daniely Zoller Cruz, Mt. Juliet, TN (US); Kenneth Jason Sanchez, Orange, CA (US); Christopher Billman, Chicago, IL (US); and Rebecca Younis, Rochester, NY (US)
Assigned to Maplebear Inc., San Francisco, CA (US)
Filed by Maplebear Inc., San Francisco, CA (US)
Filed on May 30, 2024, as Appl. No. 18/678,819.
Int. Cl. G06F 16/29 (2019.01); G06F 16/2457 (2019.01); G06Q 30/0601 (2023.01)
CPC G06F 16/29 (2019.01) [G06F 16/24578 (2019.01); G06Q 30/0623 (2013.01); G06Q 30/0641 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, performed at a computer system comprising a processor and a non-transitory computer-readable medium, comprising:
receiving, from a client device associated with a user of an online system, a request to access an interactive geographical map of sources;
retrieving a set of user data for the user, the set of user data comprising information describing a geographical location associated with the user;
identifying one or more sources within a threshold distance of the geographical location associated with the user;
retrieving a set of source data for each source of the one or more sources, the set of source data comprising information describing a set of items available at each source;
accessing a machine-learning model trained to predict a user engagement score for a source, wherein the user engagement score indicates a likelihood of one or more interactions by the user with the set of items available at the source if the source is included in the interactive geographical map of sources to be presented to the user, wherein the machine-learning model is trained by:
receiving source data for a plurality of sources,
receiving user data for a plurality of users of the online system,
receiving, for each user of the plurality of users, a label describing an interaction of a corresponding user with an item available at a source, and
training the machine-learning model based at least in part on the source data, the user data, and the label for each user of the plurality of users;
applying the machine-learning model to predict the user engagement score for each source of the one or more sources based at least in part on the set of user data and a corresponding set of source data;
selecting a set of sources from the one or more sources based at least in part on the user engagement score for each source of the one or more sources;
generating the interactive geographical map of sources based at least in part on the set of sources, wherein the interactive geographical map of sources indicates the geographical location of each source of the set of sources; and
sending the interactive geographical map of sources to the client device associated with the user, wherein sending the interactive geographical map of sources causes the client device to display the interactive geographical map of sources.