Google tests bot that will chat to your friends for you

Google has come up with a solution to your tiresome texting woes, creating a robot called Reply to do the hard work for you.

It’s based on Smart Reply, which uses artificial intelligence to suggest one-click responses to emails in Gmail, and messages in its Hangouts and Allo apps.

The expanded feature aims to take the hassle out of firing back replies in a range of popular messaging apps, including WhatsApp.

As well as single-tap responses Google is planning to enable automatic replies, for example letting people know when you are busy and can’t get to your phone.

 

Google has come up with a solution to your tiresome texting woes, creating a robot called Reply to do the hard work for you. As well as single-tap responses Google is planning to enable automatic replies, for example letting people know when you can’t get to your phone

Google’s Area 120, a workshop for experimental products under development at the Mountain View firm, is currently testing the new system.

Reply is designed to work with a number of popular messaging services, including Google Hangouts and Allo, Whatsapp, Facebook Messenger, Android Messages, Skype, Twitter direct messages and Slack.  

It has not yet been released to the public, but beta-testers are currently being sought to try out the feature more widely.

That could mean that Google is getting close to launching the AI powered bot.

Once released, it is likely that developers will need to incorporate the coding into their apps for it to work.

In an email test sent to potential testers, published by Android Police, a spokesman for the team said: ‘You probably get a lot of chat messages. And you want to be there for people, but also for people in the real world.

‘What if replying were literally one tap away?  

‘Reply can make sure to get your attention even when your phone is silent.’

One example cited in the email is using your location to send and instant response to the enquiry ‘when can you be home?’.

Reply then checks your preferred method of transport and the estimated time it’ll take to reach your home address.

This then pops up as an instant reply option. 

Other features of the Reply function include a Do Not Disturb mode.

That means when you’re driving, Reply can silence your phone and tell people who message you that you can’t chat right now. 

Reply, based on Smart Reply, is designed to work with a number of popular messaging services, including Google Hangouts and Allo, Whatsapp, Facebook Messenger, Android Messages, Skype, Twitter direct messages and Slack (stock)

Reply, based on Smart Reply, is designed to work with a number of popular messaging services, including Google Hangouts and Allo, Whatsapp, Facebook Messenger, Android Messages, Skype, Twitter direct messages and Slack (stock)

Google's Smart Reply uses the firm's neural network to intelligently analyse a message's content to suggest an appropriate response. First introduced in Gmail's Inbox, it gives users a choice of three responses to choose from based on the results of millions of email replies

Google’s Smart Reply uses the firm’s neural network to intelligently analyse a message’s content to suggest an appropriate response. First introduced in Gmail’s Inbox, it gives users a choice of three responses to choose from based on the results of millions of email replies

When you get an urgent message like ‘We’re waiting for you!’, Reply can make sure to get your attention even when your phone is silent.

Reply can also check your calendar and tell people if you’re not working, useful for making plans with friends and loved ones, or for letting professional contacts know that you’re out of the office

Google’s Smart Reply, introduced in 2016, uses the firm’s neural network to intelligently analyse a message’s content to suggest an appropriate response. 

First introduced in Gmail’s Inbox, it gives users a choice of three responses to choose from based on the results of millions of email replies.

HOW DOES ARTIFICIAL INTELLIGENCE LEARN?

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.

ANNs can be trained to recognise patterns in information – including speech, text data, or visual images – and are the basis for a large number of the developments in AI over recent years.

Conventional AI uses input to ‘teach’ an algorithm about a particular subject by feeding it massive amounts of information.   

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information - including speech, text data, or visual images

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information – including speech, text data, or visual images

Practical applications include Google’s language translation services, Facebook’s facial recognition software and Snapchat’s image altering live filters.

The process of inputting this data can be extremely time consuming, and is limited to one type of knowledge. 

A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other. 

This approach is designed to speed up the process of learning, as well as refining the output created by AI systems. 



Read more at DailyMail.co.uk