Laboratory for Applied Artificial Intelligence

In the Laboratory for Applied Artificial Intelligence, scientists, practitioners and students carry out joint research into innovative technologies that make artificial intelligence usable in concrete fields of application.

An important aim of the laboratory is to transfer knowledge from the university to business practice – mainly, but not only, to make it easier for small and medium-sized enterprises (SMEs) to access these technologies.

In so doing, we follow a strictly application-oriented approach. From our basic AI research, we only adopt those proposed solutions that promise a tangible benefit in operational application fields. In addition, we are convinced that the only way to further develop the application of AI in the business context as a whole is by combining different AI sub-areas. In this respect, we consider symbolic and sub-symbolic AI to be equally important. We do not engage in maximizing expectations of AI’s potential in a highly speculative manner, but rather provide a realistic picture of the opportunities and risks of AI for operational application.

Our subjects:

Conversational user interface

A conversational interface (CUI) is a user interface (for computers) that simulates a conversation with a real human. The idea is that users no longer communicate with the computer in an “inhuman” way, e.g. by clicking on symbols or entering syntax-specific commands. Instead, they interact using human language. They simply say the function they want the computer to perform and the computer answers in human language – supplemented by “classic” output constructs such as graphics or lists.

Further information

Intelligent chatbots and assistants for digital consulting

The digitalization of consulting initially aims to make the consulting process as similar as possible to a personal consultation by human actors. The intention is also to exploit all the advantages of computer-aided automation, such as standardization and objectivity, lower process costs and higher complexity processing capacity.

A first robust step towards a completely digital consultation is the relatively simple development of a chatbot, which is able to automatically map simple interactions with the customer. Frequently recurring service processes in particular can be handled cost-effectively by the chatbot.

The latest technology already has the potential to offer significantly more than is available from widespread button chatbots. Simple chatbots of this kind merely offer the user selection buttons to navigate through a predefined dialogue tree.

If chatbots are to achieve their full potential, they must be prepared for typical questions in the user’s natural language. This would allow simple standard questions to be dealt with cost-effectively by chatbots. Typical areas of application include service processes, product selection and product explanation processes.

The next stage of development, which will be reached within the next few years, integrates the current dialogue context, stores dialogue states in non-volatile memory, and also incorporates semantic information into the system logic. Artificial intelligence techniques are used. We are currently working hard on systems of this kind.

The aim is to establish an intelligent assistant with an advanced conversational user interface (CUI) and to create a complete digital representation of consulting processes in – initially – narrowly defined domains.

See also: Seminar: No need to fear AI – What every manager should know about artificial intelligence

Further information and contact details

Name Contact
Thomas Bahlinger Thomas Bahlinger
Prof. Dr.
Roland Zimmermann Roland Zimmermann
Prof. Dr.

Further activities at the Laboratory for Applied Artificial Intelligence

AI conference in summer semester 2019

OHM-Journal of the Nuremberg Institute of Technology: Interview with Prof. Zimmermann and Prof. Bahlinger

Future Engineering (with Fraunhofer Institute)