CTC8 – Chatbots and AI -final presentations

After two days of intense activity and a whole heap of learning for all of us, Code The City #8, our Chatbots and AI weekend came to an end at tea time on Sunday.

It couldn’t have happened without the generous sponsorship of our two sponsors: The Health Alliance, and Fifth Ring, for which we are very grateful.

The weekend rounded off with presentations of each project, four of which we’ve captured on video (see below).

Each of the projects has its own Github repo. Links are included at the end of each project description. And, two days later, the projects are still being worked on!

Team: ALISS

Team ALISS worked on providing a chatbot interface onto healthcare and social data provided via the ALISS system.

ALISS bot project : Code the City 8 from Andrew Sage on Vimeo.

You can find Project ALISS’s code here on Github.

You can also watch this video of Douglas Maxwell from the Alliance being interviewed about the weekend (although at the time of writing the video is offline due to an AWS problem).

Team: City-consult

This team aimed to make the quality of consultations better through using intelligent chatbot interfaces to guide users through the process – and to provide challenge by prompting citizens to comment on previous consultees’ input.

City-Consult bot project : Code the City 8 from Andrew Sage on Vimeo.

You can find the code for City-Consult at this Github repo.

Team: NoBot

The concept for NoBot came from an initial idea which was of a bot which would make scheduling meetings easier. That spawned the idea – what if the Bot’s purpose was to make you have fewer meetings by challenging you at every turn, and in the process the bot’s personality as a sarcastic gatekeeper was born.

NoBot project : Code the City 8 from Andrew Sage on Vimeo.

The code for Nobot lives here on Github.

Team: Seymour

Sadly there is no video of the wind-up talk for Seymour. In short the purpose of Seymour is to help you keep your houseplants alive. (More details to come).

You can find the code for Seymour at this repo on Github.

Team: Stuff Happens

We started this project with the aim to help citizens find out what was happening in the myriad of local events which we each often seem to miss. Many local authorities have a What’s On calendar, sometimes with an RSS feed. None we found had an API unfortunately.

We identified that by pulling multiple RSS feeds into a single database then putting a bot in front of it, and either through scripting or applying some AI, it should be possible to put potential audiences in touch with what is happening.

Further, by enhancing the collected data – enriching it either manually or by applying machine logic, we could make it more easily navigable and intelligible.

Expect a full write-up of the challenges of this project, and what progress was made, on Ian’s blog,

There is no video, but you an find the project code here on Github.

Team: W[oa]nder

This project set out to solve the problem of checking if a shop or business was still open for the day through a Facebook bot interface – as you with wander around, wondering about the question, as it were.

W[oa]nder bot project : Code the City 8 from Andrew Sage on Vimeo.

You can find their code here.

And finally we were joined by Rory on day two who set out to assist team Stuff-Happens through developing some of the AI around terminologies or categories. That became the:

Word Association Scorer

This is now on Github – not a bot but a set of python functions that scores a given text against a set of categories.

And Finally

We had loads of positive feedback from those who attended the weekend (both old hands and newbies) and from those who watched from afar, following progress on Twitter.

We’ve published the dates for CTC9 and subsequent workshops on our front page. We hope you can join us for more creative fun.

Ian, Andrew, Steve and Bruce
@codethecity

Final show and tell from Edinburgh

This is a last, long blog to share all the news on the ideas developed over the weekend in Edinburgh.  There is more info on twitter and on the two Storify items as well as on CodetheCity Eventifier.

We had six presentations and it was amazing to see the way ideas had developed over two days and had become live prototypes with real potential for the future!

We had a great mix of folk attending – design students from Hanzehigeschool Gronigen, young people from the Edinburgh Prewired group with Mentors from CodeBase, a number of local developers and designers who have worked on Edinburgh Council projects as well as others interested in Edinburgh data and one or two local digital companies.  We had over 70 people attending over the two days, and the buzz and focus was inspiring.

Here are the final ideas/prototypes:

Trashban – this team created Monster, munching Max – both a physical bin and an app.  The monster gets happier the more you feed it.  They looked at mapping litter reports and bins, but ran out of time, but it influenced their thinking and they would have added in locations given time.  The app encourages you to feed the monster! The final app would also include a leader board with awards for those who get rid of the most litter.

This team also had a hardware development team, built using an actual bin, which talks to you when you put litter in. It was powered by Arduino and other bits and pieces – a speaker on the inside, light sensor, and LED light – when it is disrupted by litter being thrown in the voice is activated. Everyone had a lot of fun recording litter messages! It does work but the lead developer threw in a piece of rubbish and broke it before the live demo!

Fly – an app crowdsourcing biodiversity data in the city the app issues a daily challenge to find species with a score board. The community self-moderates and data is uploaded onto a server which creates a heat map of locations in the city. Requests will come through at a specific time each day, and the rarer the species the more points there are. Incentives include virtual trophies to be won, and encourages competition. The ultimate goal is to crowdsource the data across the city.  The team managed to create an API to pull in data.

The design – homepage designed by one of the visiting Dutch students from Gronigen and images and species were researched before developing a graphical view of Edinburgh Castle – an eye catching design, with a kingfisher as the app logo.

Cyclists for cyclists – an app designed to offer a range of services for cyclists including where to get repairs, shower, park and eat as well as a chat feature. In the future it would be possible to add cycling routes, and share trips you have completed. It has the user GPS to help locate.  The idea is for it to be community driven, crowdsourcing useful information.

Edinbro built a website where people can share tasks – looking for help in their community, from anything to finding a cat to moving house. Points are awarded depending on the complexity of the task and it includes a leader board to discover who is the most helpful in your area.  They have a separate app.  Their backend was also developed so they could demonstrate adding a new request, as well as the architecture for their development.  

The Land Revival site was built by two of the Prewired coders who attended the weekend – they had the idea of mapping all the data for vacant and derelict land so people could ask for land for community projects or to buy.  Using the Council API to extract data they created a searchable site, with a full map and also a satellite map. You can view by map or list.

Data Noms is really the start of a project thought of by a local developer who is using Edinburgh Council open data.  It is an idea to create a hub to improve data for anyone using it.  Using Council data he demonstrated with one data set using programmes created to find data errors and fix them, improving the data. His example was a csv file improved from 3 star to 4 star (following the open data quality system). This development is open and be used by anyone working with data, and at specific events to help those working with data.  Although it is just a starter it is exactly what Edinburgh needs to improve its data.