Intelligent selection of images to create image narratives

A system, comprising:

• a data store operative to store images associated with a first user;
• and
• one or more computing devices performing operations to:
• access, from the data store, at least a portion of the images associated with a first user;
• obtain tags associated with the images, the tags describing individuals identified, scenes identified, and locations identified;
• determine frequencies of the tags for the images;
• identify, from the tags, first images from the images associated with the first user that depict one or more of:
• an activity that the user participates in;
• or an event the user attended;
• select a first portion of the first images based, at least in part, on the frequencies of the tags for the images and a determination that a confidence score of the first portion of the first images is above a confidence threshold, the confidence score indicating a level of confidence that tags within the first portion of the first images are associated;
• associate the first portion of the first images with an image narrative;
• and
• provide, to a client computing device, data identifying the first portion of the first images of the image narrative.

A computer-implemented method, comprising:

• accessing, from one or more data stores, images associated with a first user;
• obtaining tags associated with the images, the tags identifying faces within the images, scenes within the images, and locations of the images;
• identifying a first portion of the images to associate with a first image narrative based, at least in part, on a number of occurrences of individual ones of the tags and one or more of a specified time period, an activity, an event, or a friend identified by the tags;
• and
• providing, to a computing device, data identifying the images associated with the image narrative.