1. Towards Ubiquitous Tourist Service Coordination and Integration: a Multi- Agent and Semantic Web Approach Ho-fung LEUNG Senior Member, IEEE Dept. of Computer Science & Engineering The Chinese University of Hong Kong lhf@cuhk.edu.hk Dickson K. W. CHIU Senior Member, IEEE Dickson Computer Systems Hong Kong dicksonchiu@ieee.org

2. Ubiquitous Tourist SupportICEC2005-2 Introduction Agents - programs that act on behalf of their human users and exhibit some aspects of autonomous behavior Multi-agent information system (MAIS) used to conduct e-commerce activities Support ubiquitous access through mobile devices over wired and wireless networks As mobile devices become more powerful, intelligent software agents can now be deployed on these devices and hence also subject to mobility => peer-to-peer mobile computing Semantic Web technologies and ontology help agents to reason and MAIS more flexible and intelligent Propose next generation Ubiquitous Tourist Assistant System (UTAS) based on these technologies

3. Ubiquitous Tourist SupportICEC2005-3 Layered Infrastructure for UTAS Personal Assistance Information / Service Resources Planning… Tourist Information System Multi-agent Information System (MAIS) BDI Agents OntologyCollaboration Protocol Web-based 3-tier Implementation Architecture

4. Ubiquitous Tourist SupportICEC2005-4 MAIS Analysis and Design Methodology for UTAS Part 1 - overall architectural design Focus of this paper Part 2 - detailed design of agents Each types of agents in the UTAS domain has high potentials for further in depth research because of its emerging adoptions See our paper in HICSS37 NSS track

5. Ubiquitous Tourist SupportICEC2005-5 MAIS Overall Architectural Design Identify different categories of services for tourists with the help of ontology. If existing ontologies are inadequate, augment with required concepts. Identify different types of process to be supported. For each process, identify the major agent and then the interactions among the processes. Identify minor agents that assist the major agents to carry out these functionalities. Identify the interactions required for each minor agent type. Design the basic logics for all these agents. Identify the (mobile) platforms to be supported See if any adaptation is required

6. Ubiquitous Tourist SupportICEC2005-6 Detailed Design of Agents Design and adapt the user interface required for users to input their preferences. Customize displays to individual users and platforms. Determine how user preferences are mapped into constraints and exchange them in a standardized format. Now, we can consider automated decision support with agents. Identify the stimulus, collaboration parameters, and output actions to be performed by a BDI agent. Partition the collaboration parameters into three data sets: belief, desire, and intention. Formulate a data sub-schema for each of these data sets. Implement the schema at the data tier. Derive transformations amongst the three data sets. Implement these transformations at the application tier. Enhance the performance and intelligence of the agents with various heuristics gathering during the testing and pilot phase of the project.

7. Ubiquitous Tourist SupportICEC2005-7 Service Process Categories Ontology Maintenance and Search Requirement and Preference Management Package Planning Local Tour Planning Tourist Assistant

8. Ubiquitous Tourist SupportICEC2005-8 Tourist Assistant Agent Cluster Ontology / Knowledge Base / Tourist profiles, location, plans Requirement / Preference Management Agent Cluster Local Location Database Local Tour Planning Agent Cluster Call Center Location Alert Calendar Agents Reminder Agents User Interface Agents Vehicle Agents Local Offices Web Sites Partner Web Sites Tourist Portal Package Planning Agent Cluster Ontology Maintenance & Search Agent Cluster Alert Agent Alert Tourist Requests / Responses MAIS Overview of UTAS

9. Ubiquitous Tourist SupportICEC2005-9 Ontology Maintenance and Search Processes AgentsFunctions FlightSearch for flights (traditional way) HotelSearch for hotels (traditional way) Ontology Search Search for information from the centralized ontology in the knowledge base Web Crawler Expand the ontology and knowledge by grapping information from the Web Information Alert relevant consultant or tourist upon information update Call for industry-wide ontology

10. Ubiquitous Tourist SupportICEC2005-10 Requirement and Preference Management Processes AgentsFunctions Preference Guide the tourists to specify their requirements and preference and maintain them Ranking Ranking information and results according to user preference The ontology let the tourists know what types of information and resources are searchable and specifiable. The categorization and their attributes from the ontology can become the search criteria, options, and alternatives. The ontology records the relationships and dependencies among information and resources, e.g., better combinations. Ontology records the related web sites / subscribe for information update

11. Ubiquitous Tourist SupportICEC2005-11 Package Planning Processes Because the tourists now better understand and express their requirements and preferences with ontology, agents can reason and select from much more viable options in a flexible manner. More viable plans can be found and thus better ones can be formulated. AgentsFunctions Matchmaking Match user preferences with available services and options Cost Evaluation Evaluate the costs of matching services and options Confirmation Assist users in waiting and confirmation of bookings

12. Ubiquitous Tourist SupportICEC2005-12 Local Tour Planning Processes AgentsFunctions LocatorKeep the location of tourists and vehicles Wrapper Wrap existing third-party websites and automate programmatic interfaces to them Route Advisor Find routes for user for driving or from public transportation MapShow appropriate sections of maps to users Matchmaking Match user preferences with available services and options Cost Evaluation Evaluate the costs of matching services and options

13. Ubiquitous Tourist SupportICEC2005-13 Tourist Assistant Processes AgentsFunctions CalendarMaintain package and travel plans Reminder Remind users of their upcoming activities, bookings, and urgent information received User Interface Customize input and output to user devices (XML / XSL)

14. Ubiquitous Tourist SupportICEC2005-14 Tourists’ Benefits Anytime and anywhere assistance Multiple front-end devices increases tourists’ choice of hardware and connectivity Agents help improve reliability and robustness of messaging (especially alerts) – retry, alternatives Forward important relevant news (e.g., terrorist attack) and important messages (e.g., cancelled flight) Plan revisions Ontology helps both the tourists and the agents understand more available alternatives and options

15. Ubiquitous Tourist SupportICEC2005-15 Traveling Service Providers Costs vs. Benefits Improve the productive of their consultants and possibly the quality of recommendations Consistency of quality through pre-programmed intelligence Reduce the consultants’ workload Value-added services Improve the professional image as well as customer relationships Increase business opportunities – more partners and services

16. Ubiquitous Tourist SupportICEC2005-16 System Developer’s Perspective System development costs and subsequent maintenance efforts Our approach is suitable for adaptation of existing services and information sources by wrapping them with information agents Loosely coupled and tightly coherent intelligent software modules encapsulated in agents => manage system complexity Agents are highly reusable and adaptable Shorten the system development time via adaptation and integration Keep up with fast evolving technologies

17. Ubiquitous Tourist SupportICEC2005-17 Conclusion A pragmatic approach of developing a UTAS with an MAIS infrastructure Multiple platforms (in particular wireless mobile ones) and their integration Overview of MVM requirements and process Methodology for analysis and design of a MAIS for UTAS Discuss the design of each agent cluster Merits and applicability of our approach from the perspectives of major system stakeholders Reference model for UTAS

18. Ubiquitous Tourist SupportICEC2005-18 Further and Ongoing work Study or re-examine the technical and management perspectives of each phase and functions of the UTAS process in details Implementation MAIS architecture for other emerging domains, e.g., mobile workforce management, m-government Ubiquitous computing and context

19. Ubiquitous Tourist SupportICEC2005-19 Q&A Thank you!