Nintendo's Pokémon GO has already overtaken Candy Crush Saga to become one of the most-used apps. One of the main draws of the game for many people is that it gets players off their couches and out into the real world in search of Pokémon, and this post by Lynne Slowey on IBM’s Internet of Things blog highlights an impressive use of the Watson API to help players find these virtual creatures.
The point of the game is to find Pokémon before training them to go into battle. So, players are constantly walking around public spaces looking for the creatures that are displayed on smartphone screens using augmented reality. Players are given cues on their screens to the location of the nearest Pokémon, so front and back-end developer and part-time university lecturer in California Michael Hsu recognised an opportunity to use the Watson Visual Recognition API to play the game for him.
When approaching a Pokéstop, the Watson API takes screenshots of the app in the background at regular intervals. The screenshots are sent to the Watson Visual Recognition API for analysis, with a trained classifier able to tell if there are any Pokémon nearby from those screen shots, with the location broadcast to nearby players.
Hsu’s project ended up winning Best Use of Watson challenge at the AT&T Shape Tech Expo Hackathon in San Francisco. While it certainly fits with the collaborative gameplay ideal that encourages people to work together and help each other find Pokémon, it also raises the potential for some innovative ways to monetize the game, such as advertising, subscriptions, or to draw players to a physical business location.