Virtual Sales Agents for Electronic Commerce

Outline

Intelligent Agent Technology is a Prerequisite for Advanced WebCommerce

Five Generations of Internet Applications

What are Virtual Sales Agents?

Intelligent Web Services

XML-based Negotiation between Shopping and Sales Agents

Virtual Market Places with Human and Machine Agents

Performance Ranking of Comparison Shopping Agents

Three Generations of Web Sites

The Idea of Personalized Netbots

What is a Virtual Web Page?

Virtual Webpage Retrieved from 5 Different Servers

AiA: Information Integration for Virtual Webpages

The Generation of Virtual Webpages with PAN and AiA

Persona as a Personal Travel Consultant

The Combination of Retrieved and Generated Media Objects for Virtual Webpages

The Combination of Retrieved and Generated Media Objects for Virtual Webpages

Operational Models of Referential Semantics for Robots and Netbots (Wahlster 1999)

The Role of Ontological Annotations for the Generation and Analysis of Virtual Webpages (Wahlster 1999)

A Natural Language Agent for Finding Pre-Owned Porsche Cars

Towards Mobile and Speech-based E-Commerce Using UMTS Phones

Enhanced ECommerce through Personalization

Personified Agents Increase the User's Trust in the System's Presentation

Impact of the modality of a Presentation on the User's Trustfulness

PPP’s Persona Server implements a generic Presentation Agent that can be easily adapted to various applications

Use of a Life-like Character for Electronic Commerce

DFKI‘s PET-Technology: Flexible Realization of Virtual Sales Agents

Classification of Persona Gestures

Context-Sensitive Decomposition of Persona Actions

Extensions of the Representation Formalism

PET: Persona-Enabling Toolkit

The Persona Markup Language

Functional View of PET

The Bidirectional Control Flow on Persona-Enabled Webpages

Sending Interface Agents to Clients: Plug-Ins or Applets?

Porsche 9 11 & Boxter

Persona Active Elements (PAE)

A Virtual Sales Agent for OTTO – World’s Largest Tele-Ordering Company

DFKI’s Ecommerce Presentation Planner has been extended to accommodate for various target platforms through the introduction of a mark-up language layer

Simulated Dialogues as a Novel Presentation Technique

Presentation Teams for Advanced ECommerce

Underlying Knowledge Base

Example of a Dialogue Strategy

Multiple Interface Agents for User-adaptive Decision Support

MAUT (Multi-Attribute Utility Theory) - I

MAUT (Multi-Attribute Utility Theory) - II

MAUT - Example

Research Topics: Multiple Interface Agents

Non-Interactive Presentation Teams

Characteristics of the Interactive Presentation Scenario I

Characteristics of the Interactive Presentation Scenario II

System Architecture for Miau Multi-Party Dialogue Scenario

Multi-Agent Dialogue Control

Layer Model for Multi-Party Conversation

From Script-Based Approaches to Interactive Performances

Evaluation of Presentation Teams

Formulation of Hypotheses

Settings for the Scheduled Experiment

Dialogue Examples for the Experiment

Personalized Sales Dialogues with Presentation Teams in the Miau System

Information Extraction Agents

The Trainable Information Agents Framework (Bauer, Dengler)

Overall Architecture

Ontological Reasoning for Decision Support: Topic Maps

Domain Theory

Ontological Reasoning for Decision Support: Topic Maps - I

Ontological Reasoning for Decision Support: Topic Maps - II

Ontological Reasoning with Topic Maps Example - I

Ontological Reasoning with Topic Maps Example - II

Ontological Reasoning for Decision Support: Topic Maps - III

Programming by Demonstration - I

Programming by Demonstration - II

Programming by Demonstration - III

PbD-based Wrapper Construction for Information Agents

New approach to wrapper construction

Sample Wrapper Generation using PbD

Apply the same wrapper to a new source

Apply the same wrapper to a new source (2nd case)

PAN-Video

High Degree of Parallelism of Queries

Knowledge about a Webpage Shared by User and Agent

Example - Ontology

Query Planning

Query Planning

Query Plan Visualization

Three Levels of Mark-up Languages for the Web

M3L Integrates Three Language Families

RuleML: Ontology Extensions for Rule Knowledge

The Rule Markup Initiative

From traditional XML Representation to RDF-like Representation of RuleML Rules

Recommender Rule: Forward Markups

Recommender Rule: Backward Markup

An Example coded in RuleML 08

Two-Way Relationship Between RuleML and RDF

Research on Personalized Interface Agents brings disparate subfields in the area of intelligent systems together

Conclusion