Forsip.de Homepage Home  Imprint  Pressinformation  Intern   
News About Staff Members Contact
Deutsch  English 
  SIKOWO
  SIPBILD
  SIPaDIM
  COSIMA
  SIPKIS
  SIPREACT
  SIPRUM
  TRUSTEE
   
 
SIPREACT
  SIPREACT 2
  Context sensitive recommender systems  
Institute web site
www.abayfor.dewww.ifis.uni-passau.de

Contact
externer Linksipreact@forsip.de

Management
externer LinkProf. Dr. Burkhard Freitag
Download
DownloadFlyer (pdf, german)
Publikationen
Publications for SIPREACT
1 Project goals  and Procedure
  2 Solutions
  3 Team and contact
 
  Project goals
Situated assistance during recommendation process
In many of today’s complex markets, a sophisticated consultation is essential for customers wanting to come to informed purchase decisions. Many product domains, however, face frequent and rapid changes, necessitating enormous training expenses for the involved consultation staff. Embedded into the FORSIP research network, SIPREACT develops innovative solutions for the situated assistance of salespersons during recommendation processes.
 
  Procedure
Formalization of the product model
  To be able to permanently employ an up-to-date recommender system in spite of frequent changes of the product domain, SIPREACT aims to generate the necessary software components based on a suitable formalization of the product model. Our approach allows using the model to automatically generate the structure of the recommendation dialogue, an inference engine for customer assessment, and preference-oriented database queries.

Using this approach, changes within the product domain require only an adaptation of the associated model to be immediately reflected on the behaviour of the recommender system, including dialogue management, selling strategy, and presentation of product offers, eliminating the need for expensive programming work.

This technique is put to maximum usefulness, if the employing company already maintains a suitable product model, e.g. as a basis for regularly printed product catalogues. Marketing experts can enhance this model by some recommendation-specific pieces of information so that the model may be used in SIPREACT’s generative approach. Now, the potential for synergies becomes evident because the model has to be kept up-to-date anyway. Maintenance costs of the recommender system can therefore be greatly reduced.

To conduct the recommendation process, SIPREACT employs various innovative technologies, e.g., a flexible dialogue model based on Statecharts, or inference services about customer profiles based on probabilistic networks. Recommendations can be obtained using a ranking-oriented database querying technique which sorts the result according to the preferences of a customer.
 
model-based recommender system
SIPREACT2 support the sales dialogue with its model-based recommender system.
  Go to page
1 Project goals  and Procedure
  2 Solutions
  3 Team and contact

 
   Up           Print version

Close window
SIKOWO 1 SIKOWO 2
  • Tracking persons
  • Image processing with several video cameras
  • Situational, personalised
  • Tracking of movement
  • Recognition of pointing actions
  • Control and regulation
Close window
SIPBILD 1 SIPBILD 2
  • Evaluating video sequences
  • Controlling complex systems through gestures and facial expressions
  • Application in environments with changing conditions
  • Recognizing more facial expressions and gestures.
Close window
SIPADIM-1 SIPADIM-2
  • Controlling complex systems
    through natural speech
  • Context-dependent dialogue
    management
  • Self-Explanation of the
    System
  • Guiding the user
  • Plan-based processing
Close window
COSIMA B2B COSIMA T
  • Sales agent
  • Fully automated
  • Sales psychology dialogue
  • Individual Travel
    Composition
  • COSIMA in Tourism
Close window
SIPKIS SIPKIS 2
  • Personalised financial
    services
  • Risk and flexibility taken
    into account
  • Situations and roles
  • selection of efficient and individual portfolios
  • legal regulations
  • taxes and social capital
Close window
SIPREACT SIPREACT 2
  • Adaptive documents and workflows
  • Recommender system prototype
  • Adaptive information and assistance systems
  • Tools and author support for document variants
Close window
Role and company modelling
  • Operational information systems that adapt to situations, roles and personal preferences
  • User-friendly, individualised man-machine dialogue
  • "Just-in-time" data acquisition to meet specific needs
Close window
TRUSTEE 1 TRUSTEE 2
  • Fiduciary offers, negotiations
    and conclusions for clients
  • Anonymity guaranteed on
    the Internet
  • Application-based selection
    of products
  • Help to decide the quality
    of extracted offers