A newly-surfaced patent application suggests that Apple is trying to extend Siri’s working hours to times when a user’s iPhone is offline.
As AppleInsider reports, the patent filing, entitled “OFFLINE PERSONAL ASSISTANT”, describes how Siri queries could be performed on a given device (ie. an iPhone or iPad), rather than automatically outsourced to external servers as they are currently. The system would use machine learning to better understand contextual information around a given user request, and over time it could even determine whether a given request is better processed offline or online, when a connection is available.
While Apple is constantly filing patents pertaining to all kinds of technologies, many of which are never actually pursued in a real Apple product or service, AppleInsider’s Malcolm Owen points out that there is considerable potential for offline Siri operation after the launch of Apple’s ‘Neural Engine’ in last year’s iPhone X and a revamped version of the technology in this year’s iPhones. The Neural Engine ” is intended to perform computationally intensive tasks such as Face ID authentication and powering photography-related features, but it can also be used for tasks that use machine learning,” Owen writes, adding, “Considering the power of the second-generation Neural Engine used in the 2018 iPhone releases, it is entirely possible for an offline Siri to take advantage of the available power and machine learning capabilities to perform offline processing.”
The pursuit of offline Siri operation would also make sense in light of the growing importance of AI technology in consumer devices, particularly with respect to voice-based user interfaces. Apple competitors like Google and Samsung have been making escalating investments in their own voice-controlled virtual assistants, and this is an area where Apple hasn’t yet demonstrated clear leadership in terms of technological sophistication.