Natural Language communication between customers and products within in-store shopping environments enables new forms of product interfaces and an improved filtering and intuitive presentation of product information. In this article, we describe how customer's access to product information at the point of sale can be improved through the use of dialogue systems and heterogeneous web-based representations of product information based on formal ontologies within in-store shopping environments. After considering specific requirements of in-store shopping environments on dialogue systems, we present the model of a Conversational Recommendation Agent (CoRA), a domain-specific dialogue system, which realizes an ontology-based Natural Language Processing system for shopping situations.
Mobile technologies have the potential to change not only brick-and-mortar stores but also the way, how customers interact with physical products. They enable operational agility by means of improved availability and quality of information required by customers for in-store purchase decisions. In this paper, we show how an in-store bundling scenario can be supported by semantically enriched products (denoted as smart products) that provide dynamic product information through the use of mobile recommendation agents (MRA). We introduce therefore the concept of knowledge-based bundling that relies on smart products and MRA. In addition, we developed a MRA and evaluated its user acceptance for product bundle purchases. For this purpose, a lab experiment was conducted (n=37), which resulted in some design enhancements and promising adoption rates.
The design of ambient environments does not depend on technical issues exclusively but also on social aspects. There are several design specifications for ambient environments as well as development principles for the design of such systems, a design method should address. In this paper, we survey design methodologies considering the fulfilling of the design principles and their applicability for ambient environments. Because unprecedented, we introduce a methodology for Content-Centered Design of Ambient Environments (CoDesA) and apply this method in parts to an ambient bath environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.