Apple's Siri could one day find your iPhone photos
Need a better way to tag, sort, and find all the photos on your iPhone or iPad? An Apple patent filing suggests a new voice-controlled method.
"Siri, show me the photo of my wife and me taken at Rockefeller Center on December 20." That could eventually be a new way to locate a specific photo on your iOS device, at least according to Apple.
Published Thursday by the US Patent and Trademark Office, an Apple patent application called "Voice-based image tagging and searching" envisions a method of tapping into a voice assistant, such as Siri, to tag and find photos through various words and phrases.
iOS currently lets you sort and view the photos on your device by album, by date, and by location. But scouring for a specific photo among hundreds or more can still be time-consuming. Instead, Apple's invention would leave much of the work to Siri.
You'd start by voice tagging your photos with certain phrases, such as "my wife and me at Rockefeller Center." Since the photo would automatically be tagged with the date, telling Siri to find the "photo of my wife and me taken at Rockefeller Center on December 20" would bring up this specific shot.
The location could automatically be captured as well, meaning you wouldn't have to manually voice tag all of your photos in order to find ones based on a specific date and place. Further, the system could tag new photos based on similarities to previously tagged photos.
For example, let's say you took a series of photos in front of the Christmas tree at Rockefeller Center. You'd only need to voice tag one of those photos with that description. The technology would then compare that photo with all of the others and automatically tag them with the same location stamp.
The invention is described by Apple as follows:
A method for tagging or searching images using a voice-based digital assistant, comprising: at an electronic device with a processor and memory storing instructions for execution by the processor: providing a digital photograph of a real-world scene; providing a natural language text string corresponding to a speech input associated with the digital photograph; performing natural language processing on the text string to identify one or more terms associated with an entity, an activity, or a location; and tagging the digital photograph with the one or more terms and their associated entity, activity, or location.
A patent filing doesn't mean the technology will ever surface in the real world. But Siri can already search the Web for photos with specific names and tags. So this seems like a natural step forward.