30. März 2016

ManMachine: Building an Efficient Chat Tool Prototype

Building an Efficient Chat Tool Prototype<br/>

Artificial Intelligence (AI) has been a major theme in the last decade and numerous big companies have invested a lot of effort into the technology. Within the scope of our last ti&m garage project, we too developed a small but efficient chat tool prototype for a big company in Switzerland.

It is common knowledge that most questions asked by customers are standard inquiries about the products or the company itself. This is why we wanted to automate the process and our idea for the chat was born: A customer should be able to ask basic, product-related questions through a chat included in the website. Or in other words: If a customer on the website wants to ask a common question, a bot should be able to answer it. Of course, the customer is still provided with the option to directly speak to a call center agent.

In this context, we all remember old chat bots with inept or unrelated answers that would have failed the Turing test miserably. Therefore, to achieve the best user experience possible, we decided to solve this issue by applying the newest developments in the field of Artificial Intelligence.

Because of the nature of a garage project – it has a really short development period – it was not possible to implement the results of our research ourselves. The other option was to find a product on the market that would be a match for our problem. However, the market for AI solutions is constantly growing and can be confusing. This is why we formulated three basic criteria for our required system:

  1. It should be possible to implement in six weeks.
  2. It should be based on the newest findings in AI research.
  3. It should provide the best results possible, in more than one language.

One of our first guesses was IBM Watson, one of the top cognitive systems that has thought processes similar to a human. Unfortunately, Watson did not pass our criteria. Firstly, it would not have been possible to implement the technology into our system within only six weeks – it already took us three weeks to get in touch with IBM. Secondly, the technology Watson is based on wasn’t an exact fit to what we had in mind and thirdly, we did not have the possibility to test Watson on our own. All in all, Watson was out of the race.

The next promising product we looked at was FreeHAL, an open source self-learning dialog bot based on a semantic net. After a first look and a rough implementation, FreeHAL was looking really good. The technology was simple to implement into our product and it could communicate in German as well as English. However, after playing around with FreeHAL, we were disappointed as the AI was not quite as good as we had initially expected. Most of the answers turned out to be unrelated to the initial question.

We had to find another solution. Fortunately, we were able to find an interesting product called wit.ai, a cloud based AI for natural language processing grounded in the latest research. However, the first impression was not promising as the examples on the website where not exactly within the scope of our problem. Nevertheless, by digging a little deeper, we managed to find exactly what we needed and the implementation into our system turned out to be simple.

We only had to call the API of wit.ai with the question asked by the user and the cloud service would then return an answer. On the service page of wit.ai, we were able to define a basic catalogue of topics and answers. After testing the product, we got some really nice results and decided to go with wit.ai for our project.

All in all, it was a pleasure to implement and play with all these new products in the field of artificial intelligence and we noticed that in most cases, the implementation of complex systems are not necessary to proof a concept. Working in a ti&m garage was fun for all the participants and lead to interesting insights, cool products and a good time all around.


Martin Fabini
Martin Fabini

Martin Fabini studierte Mathematik an der Universität Göttingen und ist seit mehr als 20 Jahren in der IT tätig. Mit einem Hintergrund als Software-Entwickler und Architekt hat er im Verlaufe der letzten Jahre vielfältige Managementaufgaben und Beratungsmandate wahrgenommen.

Related Articles

sbb wind of change
Wind of Change

Die digitale Transformation der SBB und wie uns eine differenzierte Cloud-Strategie dabei unterstützt.

Mehr erfahren
Karin_Mathys_lead
Die digitale Transformation verändert Verhalten und Erwartungen der Kunden

Nach und nach verlagern sich Teile der Customer Journey in den digitalen Kanal. Trotzdem bleibt die persönliche Beratung für den Kunden wichtig. Um die konkreten Erwartungen zu erfüllen, müssen Unternehmen bei der Gestaltung ihres Angebots die Kunden und ihre Bedürfnisse ins Zentrum stellen.

Mehr erfahren
google datacenter
AI und die Cloud – ein Patentrezept für alles?

AI hat sich heute zum wahren Modewort entwickelt. Jedoch ist der Begriff inzwischen so emotional aufgeladen, dass Realität und Vorstellung sehr weit auseinanderliegen. Dieser Artikel soll ein Erklärungsversuch darstellen, was AI heute schon leisten kann und warum Cloud-Technologien dabei so eine entscheidende Rolle spielen.

Mehr erfahren
Cloud Act Lead image
CLOUD Act und Data Residency – Ist amerikanischen Cloud Providern noch zu trauen?

Durch den CLOUD Act müssen US-Firmen Daten auch aus ausländischen Rechenzentren bei Anfrage an US-Behörden ausliefern. Firmen, die mit US-Cloud-Providern zusammenarbeiten, müssen sich dieser Gefahr bewusst sein, wie ti&m-Surfer Bernd Leinfelder in seinem Blog-Beitrag herausarbeitet.

Mehr erfahren
API 750x410
Wie sich mit APIs Geschäftsmodelle verändern

IT-Systeme vernetzen sich immer stärker. Application Programming Interfaces, kurz APIs, sind Anwendungsprogrammierschnittstellen zwischen IT-Systemen und werden daher 2017 stark an Bedeutung gewinnen. Ihre erfolgreiche Anwendung erfordert die Zusammenarbeit von Business, IT-Entwicklung und IT-Betriebsmitarbeitern in kleinen, interdisziplinären Teams von 6-8 Personen.

Mehr erfahren
emily-morter-188019-unsplash
Cloud Computing – Macht NoOps den IT-Betrieb bald überflüssig?

Während viele Unternehmen noch damit beschäftigt sind, im Rahmen ihrer agilen Transformation eine DevOps-Kultur einzuführen, entwickelt sich im Tooling-Bereich schon der Begriff NoOps, um weitere Schritte auf dem Weg zur vollständigen Automatisierung im Software-Betrieb zu beschreiben. Braucht es in Zukunft überhaupt noch ein Operations-Team?

Mehr erfahren