IIC Journal of Innovation 10th Edition | Page 15

Intelligent Realities For Workers Using Augmented Reality, Virtual Reality and Beyond constraints. Both VR and AR reality analytics apps must deal with the basic problem of putting context first. If users are going to gain value from having their analytics in context, then the analytics cannot overly obscure the context. In VR, that means that a 3D model of a factory should be visually dominant if it is to properly contextualize a chart about some aspect of the factory’s operations. An artificial expert could also carry this burden or work in concert with a human expert. The AI chatbot practices 20 seen at call centers can be brought to bear. Just as chatbots replace first level call center representatives, they can alleviate remote experts from first level work. Then, a single remote expert can cover more junior workers and focus on tougher problems. Digital Twin Overlay As UI space is at a premium, it becomes important to use that space wisely. The challenge is to give the user the best information for their role at that point of time and for their current location. AI can help solve that problem. Rather than forcing the worker in to a data exploration UI paradigm which would require many selection actions, AI can make content selections on behalf of the worker. The Industrial Internet Consortium defines a digital twin as “a digital representation of an entity, including attributes and behaviors, sufficient to meet the requirements of a set of use cases.” 21 It is not only data about a physical asset, like its service history. A good digital twin takes the information about the design, production and operational life of the asset and virtualizes it in to a digital asset that can be tested and modified in ways that you would never treat an operating physical asset. Instead of a single expensive crash test of a car, you could perform millions of crashes virtually. Rather than a couple of turns around a test track, a car could be virtually driven for millions of miles across multiple tests with different service histories. Such tests could then be used to feed machine learning neural nets which are then queried when servicing the real asset. Artificial Remote Experts In the popular remote expert use case for AR 19 , the remote expert could be human or artificial. For example, a field technician wears an AR HMD and a human remote expert can see what the technician is seeing through the head-mounted camera. The remote expert could also access equipment history and metrics. 19 E. Hadar et al., “Hybrid remote expert - an emerging pattern of industrial remote support,” CAiSE Forum, 29th International Conference on Advanced Information System Engineering, Essen, Germany, June 2017. Available: http://ceur-ws.org/Vol- 1848/CAiSE2017_Forum_Paper5.pdf 20 K. Nimavat and T. Champaneria, “Chatbots: An Overview. Types Architecture, Tools and Future Possibilities,” International Journal for Scientific Research & Development, October 2017 https://www.researchgate.net/publication/320307269_Chatbots_An_overview_Types_Architecture_Tools_and_Future_Possibi lities 21 Q1 Digital Twin Interoperability TG Meeting Minutes, Feb 2019, Available: https://workspace.iiconsortium.org/higherlogic/ws/groups/interop-tg/download/25418/latest - 11 - March 2019