Conversational agents (CA) occasionally fail to understand the user's intention or respond inappropriately due to natural language complexity. These conversational breakdowns can happen because of low intent and entity prediction confidence scores. A promising repair strategy in such cases is that the CA proposes to users likely alternatives to proceed. If one of these options matches the user's intention, the breakdown is repaired successfully. We propose that successful repairs should be followed by a learning mechanism to minimize future breakdowns. After a successful repair, the CA, user, or both can learn each other's specific phrasing. This prevents similar phrasings from causing reoccurring breakdowns. We compared user preferences for these learning mechanisms in a scenario-based study with manufacturing workers (). Our result showed that users first prefer to share the learning burden with the CA (61.3%), followed by entirely outsourcing the learning burden to the CA (60.7%) as opposed to themselves.

@en

By applying data analytics to product usage information (PUI) from combinations of different channels, companies can get a more complete picture of their products' and services' Mid-Of-Life. All data, which is gathered within the usage phase of a product and which relates to a more comprehensive understanding of the usability of the product itself, can become valuable input. Nevertheless, an efficient use of such knowledge requires to setup related analysis capabilities enabling users not only to visualize relevant data, but providing development related knowledge e.g. to predict product behaviours not yet reflected by initial requirements. The paper elaborates on explorations to support product development with analytics to improve anticipation of future usage of products and related services. The discussed descriptive, predictive and prescriptive analytics in given research context share the idea and overarching process of getting knowledge out of PUI data. By implementation of corresponding features into an open software platform, the application of advanced analytics for white goods product development has been explored as a reference scenario for PUI exploitation.

@en

A product’s value is increasingly determined by the services supporting it. Complex Product-Service Systems (PSS) – combinations of services and products – are in demand. Product usage information (PUI), that is, information about how an individual product is used, is rapidly becoming a valuable asset to industry to help inform service offers throughout the product lifecycle. Conventionally, information about how a product is used is gathered in customer relations and MRO (maintenance, repair and overhaul) processes via channels such as repair logs, call centres or helpdesks. Today, new channels of PUI are emerging from the digitalization of products, the Internet of Things, Cyber-Physical Systems, Internet PUI sources and social media. However, there is a lack of a methodological approach which companies use to select the right PUI source for the design of services, and vice-versa, to understand which value-added services can be offered using information already generated by sensors embedded into their products or available on the Internet or in social media. This contribution is intended to show an avenue of research towards such a methodology.@en