A Knowledge-Based Framework for the Rapid Development of Conversational Recommenders

Web-based sales assistance systems are a valuable means to guide online customers in the decision-making and product selection process. Conversational recommenders simulate the behavior of an experienced sales expert, which is a knowledge-intensive task and requires personalized user interaction according to the customers’ needs and skills. In this paper, we present the Advisor Suite framework for rapid development of conversational recommenders for arbitrary domains. In the system, both the recommendation logic and the knowledge required for constructing the personalized dialog and adaptive web pages is contained in a declarative knowledge-base. The advisory application can be completely modeled using graphical tools based on a conceptual model of online sales dialogs. A template mechanism supports the automatic construction of maintainable dynamic web pages. At run-time, a controller component generically steers the interaction flow. Practical experiences from several commercial installations of the system show that development times and costs for online sales advisory systems can be significantly reduced when following the described knowledge-based approach.

[1]  Ivar Jacobson,et al.  The unified modeling language reference manual , 2010 .

[2]  Oscar Pastor,et al.  Extending a Conceptual Modelling Approach to Web Application Design , 2000, CAiSE.

[3]  James Goodwill.  Mastering JSP Custom Tags and Tag Libraries , 2002 .

[4]  Jeff Gray,et al.  Domain-Specific Modeling with Visual Languages , 2004 .

[5]  Dietmar Jannach,et al.  Building on-line sales assistance systems with ADVISOR SUITE , 2004, SEKE.

[6]  Stephen Travis Pope,et al.  A Description of the Model-View-Controller User Interface Paradigm in the Smalltalk-80 System , 1998 .

[7]  Hendrik Blockeel,et al.  Web mining research: a survey , 2000, SKDD.

[8]  Jim Conallen,et al.  Building Web applications with UML , 1999 .

[9]  Fabio Abbattista,et al.  A Framework for the Development of Personalized Agents , 2003, KES.

[10]  Gustavo Rossi,et al.  Engineering Web Applications for Reuse , 2001, IEEE Multim..

[11]  Stefano Ceri,et al.  Web Modeling Language (WebML): a modeling language for designing Web sites , 2000, Comput. Networks.

[12]  Dietmar Jannach,et al.  ADVISOR SUITE - A Knowledge-Based Sales Advisory-System , 2004, ECAI.

[13]  Thomas Schiex,et al.  Valued Constraint Satisfaction Problems: Hard and Easy Problems , 1995, IJCAI.

[14]  Derek G. Bridge,et al.  Towards Conversational Recommender Systems: A Dialogue Grammar Approach , 2002, ECCBR Workshops.

[15]  Gustavo Rossi,et al.  A Software Architecture for Structuring Complex Web Applications , 2002, J. Web Eng..

[16]  Alex Berson,et al.  Building Data Mining Applications for CRM , 1999 .

[17]  Pat Langley,et al.  A Personalized System for Conversational Recommendations , 2011, J. Artif. Intell. Res..

[18]  Liliana Ardissono,et al.  A Framework for the Development of Personalized, Distributed Web-Based Configuration Systems , 2003, AI Mag..

[19]  Stefano Ceri,et al.  Conceptual Modeling of Data-Intensive Web Applications , 2002, IEEE Internet Comput..

[20]  Ivar Jacobson,et al.  Unified Modeling Language , 2020, Definitions.

[21]  Liliana Ardissono,et al.  Personalising On-Line Configuration of Products and Services , 2002, ECAI.