Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

A few others

- Neighbor wrath saver: Constantly listen for shower and other bathroom noises and shut off any alarms if the user is deemed to be inside the bathroom and unable to reach the phone.

- Maps optimizer: Constantly listen to the accelerometer and if you determine the pattern to be the person running and there is a Facebook or Google calendar event starting within 30 minutes, automatically start navigating to it. If there are multiple simultaneous events in the calendar, try to determine which one the user is running towards and help the user reach that particular event. But also listen to the microphone and stop navigation if the user yells "shut up". Increase the font size and button size as well if the user is trying to operate phone while running.

- Caltrain ticket optimizer: If your GPS location is approaching a Caltrain station and the train is due to arrive within 3 minutes such that you're worried about purchasing a ticket in time, automatically download the Caltrain app and purchase a ticket for you so you don't have to fiddle with the machine. Work with Caltrain Inc so that it can unpurchase the ticket if you don't actually board the train

- Laundry optimizer: Automatically listen for sounds of laundry machines starting and remind you in 35 minutes later if it's the sound of a washer starting, or 45 minutes later if it's the sound of a dryer starting

- Cooking optimizer: Use front camera to determine if the user's hand is full of flour, oil, egg and if so, enable voice control of the UI of sorts e.g. "scroll down slightly", "kill that popup", "don't lock screen for the next hour" etc.

- Use the phone as a bluetooth mouse using the flashlight, rear camera, and accelerometer to determine motion on the table.

...



Everything but the last idea seem very annoying, prone to failure and highly battery-draining


In particular, most of these require always on audio and in some cases video scanning and recognition. My distant memory is that you can record audio on a fairly small processor and power budget, but video is expensive no matter what you do, and running the sort of pattern recognition or worse yet machine learning needed to actually do anything useful with it would be murder on your battery if you were unplugged and on performance even if you weren't. (This might change with the wide availability of hardware specifically designed for these tasks (TPUs), but we're not quite there yet and I don't know how general that will ever be)


> very annoying

They should use machine learning to learn how to not be annoying then. This is possible, it's just big companies have too much momentum to make useful products nowadays

> highly battery-draining

Having demand will will be motivation for better battery research.


Why u think there would be demand? I see none




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: