Determining relevant information based on user interactions

A method of operating a computing device, the method comprising:

• receiving data from a data source that is local to the computing device;
• receiving a set of signals describing a current environment of a user;
• receiving relevance information from the data source;
• providing, using a machine learning model at the computing device, a relevance score for each of multiple data items based at least in part on a relevance metric determined for each of the multiple data items by applying the set of signals to the received relevance information;
• sorting the multiple data items based at least in part on the relevance scores;
• and
• providing, as output with the computing device, one or more of the sorted multiple data items.

A computer program product comprising code stored in a non-transitory computer-readable storage medium, the code comprising:

• code to receive data a local data source;
• code to receive a set of signals describing a current environment of a user;
• code to receive relevance information from the local data source;
• code to provide, using a machine learning model, a relevance score for each of multiple data items based at least in part on a relevance metric determined for each of the multiple data items by applying the set of signals to the received relevance information;
• code to sort the multiple data items based at least in part on the relevance scores;
• and
• code to provide, as output, one or more of the sorted multiple data items.