Apple patent may foretell an end to iPhone autocorrect Tourette’s
An Apple patent application just published by the US Patent Office shows that the masterminds of Cupertino have figured out (or hope to figure out) a cunning way to work out what words you're going to tap into your little Jesus mobe before you type it.
The US Patent Office has not yet granted the patent, but in accordance with its policy of publishing patents after a certain amount of time has elapsed since their submission (this dates from Dec 2010), it has unveiled the Cupertino application titled: "Combining timing and geometry information for typing correction" .
By recording just where and how fast your hot little fingers fall on the screen as you type certain words, Apple aim to build up a user profile for you - information about your identifiable finger habits.
Pulling your unique typing habits into an algorithm along with the standard dictionary data should allow Apple to score possible replacement words by likelihood: judging for instance whether you meant to write "chocolatier" or "cock-licker" - a confusion that an autocorrect substitution generated for one iPhoner.
Current models of predictive text depend on standardised dictionary word variations to predict what words the iPhone might be about to type. Sometimes they include data about words that users commonly mistype.
iPhone autocorrect is famous for its contextually odd substitutions, with a whole blog devoted to the worst examples. "P sense hope sexy" for "Poughkeepsie", "asshole" for "apple sauce" or any number of words for genitalia.
(Source: theregister.co.uk)
