Sabine Janzen

Knowledge-Based Bundling of Smart Products on a Mobile Recomendation Agent

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.

Reasoning on Smart Products in Consumer Good Domains

Ambient intelligence technologies rapidly change product capabilities but also the way how users interact with physical products. This product-centered stance requires an instance-centered Product Life Cycle (iPLC) view which perceives products as autonomous actors performing in physical situations which leads to the concept of smart products. Smart products adapt to situations on the basis of internal representations. We present a generic extensible data model, called Smart Product Description Objects (SPDO), whose semantics are described by formal and machine-readable ontologies. SPDO instantiations are computational counterparts of physical product instances. We exemplify the use of SPDO by inferring similarity sets of products within a fashion domain.

Pattern-based approach for designing with diagrammatic and propositional conceptual models

A conceptual modeling approach for Ubiquitous Information Systems (UIS) is presented as a central part of a UIS design methodology. Three conceptual models are used for step-wise derivation of machineexecutable design models for distributed service infrastructures: narratives, pattern-based diagrammatic conceptual models (Pre-Artifacts), and formalized propositional conceptual models.

A methodology for content-centered design of ambient environments

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.

Linkage of heterogeneous knowledge resources within in-tore dialogue interaction

Dialogue interaction between customers and products improves presentation of relevant product information in in-store shopping situations. Thus, information needs of customers can be addressed more intuitive. In this article, we describe how access to product information can be improved based on dynamic linkage of heterogeneous knowledge representations. We therefore introduce a conceptual model of dialogue interaction based on multiple knowledge resources for in-store shopping situations and empirically test its utility with end-users.

Towards Benevolent Sales Assistants in Retailing Scenarios

Non-collaborative dialogues like sales dialogues are characterized by congruent intentions, i.e. intentions that are agreed by dialogue partners, and conflicting intentions. We will refer to these intentional structures as mixed intention sets. In this paper, we will investigate dialogue systems that are benevolent towards a dialogue partner, i.e. benevolent agents try to find a fair balance between partner intentions and agent intentions in particular with respect to conflicting intentions. For the class of question-answering dialogues, we propose a model for the intelligent generation of answers considering mixed intention sets and demonstrate its application in the retailing domain in form of a benevolent sales assistant (BSA). BSA processes mixed intention sets in a strategic way by means of a game-theoretical equilibrium approach to find a fair balance between intentions of dialogue partners. We evaluated the BSA by a run-time analysis of 500 simulated sales dialogues between customers and retailers and show how the sales assistant strategically generates answers considering mixed intention sets in retailing scenarios.

Towards design engineering of ubiquitous information systems

Designing complex information systems is a task performed by design teams with team members coming from different domains with different expertise. Shared understanding between members of a design team throughout a project is still a challenge. A design framework is presented that integrates individual design knowledge, explicit design knowledge used by design teams, and computational design knowledge. For each type of design knowledge, several modeling languages for expressing conceptual models are known. Translation processes between these characteristic design knowledge explications are introduced. Core elements of this design framework, i.e., modeling languages and translations, are discussed by a Ubiquitous Information System (UIS) development project that was conducted over the period of several years.

Towards a Transition to Tangible Commerce : Design and Evaluation of Conversational Product Interfaces

Ubiquitous computing technologies disclose new means for consumer product designs that allow products to adapt their behaviour and in particular communication to consumer needs and to interact with other products. In this sense, products become smart. Dialogues between products and consumers require new communicative product interfaces. Because unprecedented, we investigate an implementation of a dialogue- based product interface that is virtually bound to a product via a mobile recommendation agent (MRA) on a PDA and thus reuses knowledge learned by mobile applications. The dialog system of the MRA is tested with the system usability scale (SUS) for a global assessment of its usability to obtain product information (N=47). This preliminary study resulted in promising SUS scores as well as valuable qualitative feedback for future work.

Finding the Middle Ground - A Model for Planning Satisficing Answers.

To establish sophisticated dialogue systems, text planning needs to cope with congruent as well as incongruent interlocutor interests as given in everyday dialogues. Little attention has been given to this topic in text planning in contrast to dialogues that are fully aligned with anticipated user interests. When considering dialogues with congruent and incongruent interlocutor interests, dialogue partners are facing the constant challenge of finding a balance between cooperation and competition. We introduce the concept of fairness that operationalize an equal and adequate, i.e. equitable satisfaction of all interlocutors’ interests. Focusing on Question-Answering (QA) settings, we describe an answer planning approach that support fair dialogues under congruent and incongruent interlocutor interests. Due to the fact that fairness is subjective per se, we present promising results from an empirical study (N=107) in which human subjects interacted with a QA system implementing the proposed approach.

Towards a transition to tangible commerce

Ubiquitous computing technologies disclose new means for consumer product designs that allow products to adapt their behaviour and in particular communication to consumer needs and to interact with other products. In this sense, products become smart. Dialogues between products and consumers require new communicative product interfaces. Because unprecedented, we investigate an implementation of a dialogue-based product interface that is virtually bound to a product via a mobile recommendation agent (MRA) on a PDA and thus reuses knowledge learned by mobile applications. The dialog system of the MRA is tested with the system usability scale (SUS) for a global assessment of its usability to obtain product information (N=47). This preliminary study resulted in promising SUS scores as well as valuable qualitative feedback for future work.