Towards Automatic building of Human-Machine Conversational System to support Maintenance Processes
This addresses the scalability issue in knowledge management for companies adopting Industry 4.0, though it is incremental as it builds on existing text mining techniques.
The research tackled the problem of manually building dialog systems for industrial maintenance by proposing a methodology to automatically construct them from technical documentation, resulting in a taxonomy network for future chatbot interactions.
Companies are dealing with many cognitive changes with the introduction of the Industry 4.0 paradigm. In this constantly changing environment, knowledge management is a key factor. Dialog systems, being able to hold a conversation with humans, could support the knowledge management in business environment. Although, these systems are currently hand-coded and need the intervention of a human being in writing all the possible questions and answers, and then planning the interactions. This process, besides being time-consuming, is not scalable. Conversely, a dialog system, also referred to as chatbot, can be built from scratch by simply extracting rules from technical documentation. So, the goal of this research is designing a methodology for automatic building of human-machine conversational system, able to interact in an industrial environment. An initial taxonomy, containing entities expected to be found in maintenance manuals, is used to identify the relevant sentences of a manual provided by the company BOBST SA and applying text mining techniques, it is automatically expanded. The final result is a taxonomy network representing the entities and their relation, that will be used in future works for managing the interactions of a maintenance chatbot.