Chatbots in self-service personnel management

by | May 27, 2021

Chatbots in Self-Service Personnel Management – A Management Paper by Students of JKU Linz

Artificial Intelligence and Machine Learning – the buzzword of the new era, which is also increasingly finding its way into personnel management. Together with our cooperation partner TD Trusted Decisions, a German/Austrian consulting company that has a special focus on business decisions from different angles and also wants to increasingly incorporate AI and Machine Learning into its activities with the pulse of the times, we have set out to sprinkle another pinch of digitalization with artificial intelligence in HR management as well.

The goal of the project was to develop a concept for the use of chatbots for the processing of investment applications based on the theoretical state-of-the-art and empirical surveys in companies and to implement and evaluate it as a prototype.

The young and recognized Design Science Research research method with its 6-step model (by Gregor and Hevner, 2013) guided us on our research for an efficient process and its prototypical implementation when making investment requests with a focus on computers/laptops.

Empirical surveys for problem identification and target definition derived therefrom

On the basis of eleven interviews with a wide variety of companies, we surveyed the current process of various investment applications, the general experience with chatbots and the attitude towards chatbots used in the future. Currently, many investment applications are still submitted in writing – here we see potential and need to digitize this process in the future with the help of a chatbot. Our goal, concretely defined from these surveys, focuses on a chatbot prototype for computer/laptop investment requests that both digitizes and makes more efficient the current manual process.


Chatbot training with Dialogflow

For the prototypical implementation of the chatbot, the Google provider Dialogflow was used, as it is user-friendly and easy to handle even for more complex implementations.

Qlik Select Solution Provider

Training schedule

  1. Creation of Intents (= intention of the user, training sets)
  2. Creation of entities (reference to keywords)
  3. Action and Parameters react to entities (specific terms)
  4. Triggering a prompt if the entity does not contain the question (counterquestions)
  5. Return of possible answers (response) from the chatbot
  6. Combining all intents into one (intent trains agent)
  7. Integration on other devices (agent corresponds to applications)

Functioning prototype

The user is guided by questions about the name, type of investment (PC, laptop), manufacturer, storage capacity, possibly desired interfaces, monitor size + resolution. The user’s answers are summarized at the end and can be forwarded to the responsible person for further processing.

The management paper was prepared by Claudia Haas, Sabine Lindner, Samed Esen, Emre Karakus, Ilker Akceylan, Mustafa Baghdadi.

We thank the students of the JKU Linz for a great cooperation.

You might also be interested in.

Active Intelligence – Always on the pulse of time

Active Intelligence – Always on the pulse of time

Distortions – How perceptual errors jeopardize success

Distortions – How perceptual errors jeopardize success

The Future of Decision Making – Episode: HOT DECISIONS -.

The Future of Decision Making – Episode: HOT DECISIONS -.

Automation in Controlling: Success Factor or Stumbling Block for Companies?

Automation in Controlling: Success Factor or Stumbling Block for Companies?

Sign up for our newsletter.


Get the latest information for your management and controlling, about our events and trainings, about product and partner news and much more.

Thank you. Please check your emails to confirm the registration.