There’s been a lot of buzz around this ominous Industry 4.0 in Europe for quite a while now. However, it’s not that clear at all what this term means really. And it appears to be even less clear how Industry 4.0 will arrive in the production reality.
The only thing that’s clear is: The traditional industries are becoming more and more digitalized. Products and production processes are cross-linked and the knowledge about processes and assembly is being slipped into production system exceedingly. The goals are clear: A higher degree of automation, the development of intelligent monitoring processes and autonomous decision processes as well as the optimization of the value-added chain.
Efficiency is a keyword that hovers above all this – and speech and gesture control are playing key roles in boosting efficiency, as they allow the user to access information and influence processes while performing a primary task like, for example, the set-up process.
APPLICATION EXAMPLES FOR MULTIMODAL HUMAN-TECHNOLOGY INTERACTION
In the scenario for an interactive handbook, a virtual guidebook attends the user in production processes, provides support for service tasks and serves quality assurance. Production and information relevant for production can be made available individually and depending on the situation, very accurate access to knowledge sources is provided, and the interaction can happen touch-free. Additionally, the user can be supplied with flexible means of information presentation like multimedia content, interactive sequences, animations, even the inclusion of live data via backend systems is possible (building plans and check lists…).
It’s a no-brainer really, but faces some challenges in reality: voice control of machines and processes. No matter if for data retrieval from ERP systems, data collection for example in quality assurance, or for switching of operation modes of machines and devices – the advantages are obvious: The user saves time (instead of hand-written notes that have to be entered into a computer later there’s only one step necessary anymore); by avoiding media disruption, data quality is increased; and the overall gain in efficiency due to the simultaneous execution of several individual operations is enormous. The addressed challenges are:
- Miking must be defined and installed according to the situation.
- Intelligent filter functions must be integrated in order to suppress background noises and improve signal quality.
- There may be a need for the deployment of additional out- and input devices like data glasses, gesture control etc.
The added value of voice control and assistance solutions is clear: Most workers are wearing gloves or they need their hands for the use of tools or similar devices. If the hands are free, the worker is able to perform his or her tasks more efficiently. Also in the healthcare sector alternative interaction forms generate relevant added value (speaking of sterility). Speech is the most efficient medium for communication, and it enables us to delegate even complex tasks to a system or a machine very easily. Voice control encapsules several different applications and data sources to a unified control interface (e.g. local functionalities and backend services), offering easy and fast access to heterogeneous data sources. Alternative forms of interaction can even enable users with physical or sensory impairments (e.g. poor eyesight or motoric limitations) to operate machines or technology in the first place, crucially contributing to accessibility. In the area of automation and quality assurance, interactive manuals for production tasks, makeready processes or the manufacturing of parts can be deployed. Data quality is increased due to the avoidance of media disruption, e.g. the omission of hand-written notes and the direct input of data into the existing IT systems.
But intelligent speech solutions can also contribute to efficiency increase in the usage of business software. Semantically complex searches like “What were our strongest selling products in April?” or text fill in assistance in dialog with the system help saving time and cost and relieve the user from stress. The dialog aspect is central in the application of speech technology solutions as a personal assistance: In case there are several contacts stored with the same name, the system will proactively ask for the desired number or leads intelligently through a process like completing a new calendar entry:
User: „Call Mrs. Miller!“
System: „Mrs. Miller of Test GmbH or of Example AG?“
User: „Create a new appointment tomorrow a 4 p.m.“
System: „Please add a subject!“
Voice control and assistant systems can be deployed on virtually any kind of mobile or stationary devices like smart glasses, smart watches, desktop computers and work stations, smart phones and tablet computers. Also they can run purely embedded, as hybrid or cloud-based services. The use of all functionalities of course is possible hands-free, also in a multi-modal way – i.e. not only via voice but also via touch or gesture, namely interwoven. The added value of such a way of working opposed to the traditional one is (often parallel to the use in a production environment) obvious:
- Productivity and efficiency in the use of business software are increased through the application of intelligent voice control and assistance systems.
- Efficient semantic search in big volumes of data is enabled in an easy way.
- Creation of intelligent system suggestions („Recommendation Engine“).
- Proactive queries of the system if it is lacking information, e.g. while filling in forms.
- Homogenous, intuitive access to heterogenic data and information sources.
- Inclusion of context and personalization information.
With (optionally multimodal) voice control and dialogic assistance systems, men and technology can grow together in their work environment – following the rules of the human. Technology learns to adapt to the human ways of working by adopting human means of communication as a standard. Only in this way can the human and technological worlds be interwoven efficiently, always keeping the human factor as a reference and supreme authority.