1. Context Awareness: From Dream to Reality Norman M. Sadeh School of Computer Science Carnegie Mellon University Research Sponsors: DARPA/DAML, IBM, Boeing, HP, Symbol, EU IST

2. Copyright ©2003 Norman Sadeh Why Context Awareness? Can no longer assume the user’s undivided attention Can no longer assume the user’s undivided attention  Talking to friends or colleagues, driving, etc. Time critical nature of many tasks Time critical nature of many tasks  Finding the nearest gas station or the next flight back home Limited input/output functionality Limited input/output functionality

3. Copyright ©2003 Norman Sadeh Sources of Contextual Information A user’s context information is distributed across a number of disparate resources A user’s context information is distributed across a number of disparate resources  Calendar  Location tracking  Address book  Buddy lists or organizational DB  Weather  etc. Available resources vary from one user to another Available resources vary from one user to another  …and over time

4. Copyright ©2003 Norman Sadeh No Interoperability Ad hoc/proprietary standards Ad hoc/proprietary standards Applications are hardwired to different sources of contextual information Applications are hardwired to different sources of contextual information Minimal re-use Minimal re-use High development and maintenance costs High development and maintenance costs  No economies of scale  Lack of an open architecture

5. Copyright ©2003 Norman Sadeh Vision A growing collection of context-aware agents that users can pull into their own personal environment (Semantic e-Wallet) A growing collection of context-aware agents that users can pull into their own personal environment (Semantic e-Wallet)  Just like users today download ring tones on their mobile phones – except that they might reside on a server As a copy of an agent is pulled into a user’s personal environment, it accesses the user’s semantic e-Wallet to discover and access relevant contextual resources (automatic customization) As a copy of an agent is pulled into a user’s personal environment, it accesses the user’s semantic e-Wallet to discover and access relevant contextual resources (automatic customization)

6. Copyright ©2003 Norman Sadeh Semantic Web Approach Ontologies to explicitly represent and reason about: Ontologies to explicitly represent and reason about:  Personal/Contextual Resources  Location tracking, calendar, organizational resources, messaging resources, preferences, access devices, etc.  Contextual attributes  e.g. location, calendar activities, social or organizational context, device characteristics, etc.  Preferences  Including access control/privacy preferences  Web services  Automated service discovery, access, composition and execution

7. Copyright ©2003 Norman Sadeh Personal Resource Ontology: An Example Personal Resource Activity Information Resource Location Information Resource List of Friends Sprint PCS Location Tracking CMU Location Tracking Microsoft Outlook Calendar IS-A INSTANCE

8. Copyright ©2003 Norman Sadeh MyCampus Project Motivation: Motivation:  Campus as “everyday life microcosm” Objective: Objective:  Enhance campus life through context-aware services accessible over the WLAN Methodology: Methodology:  Involve stakeholders in the design  Students and other members of the community  Evaluate and extrapolate to other environments  Mobile Commerce, Mobile Enterprise, etc.

9. Copyright ©2003 Norman Sadeh System Architecture Wireless LAN Calendar Location Tracking Internet and Intranet Semantic Web-enabled Services Task-Specific Agents e-Wallet User’s Personal Environment Social Context Preferences Semantic Web-enabled Personal Resources Personal Resource Directory (incl. Access Control) Personal Resource Ontologies Contextual Ontologies Personal Preference Ontologies Service Ontologies Semantic Web Service Directory

10. Copyright ©2003 Norman Sadeh Example: Restaurant Concierge Contextual Attributes: Contextual Attributes:  Location: Where am I?  Calendar  How much time until my next meeting?  Where’s my next meeting?  Weather: Is it raining, sunny, etc.?  Budget Preferences: Preferences:  Static & Context- sensitive preferences

11. Copyright ©2003 Norman Sadeh Current Status Prototype working on Carnegie Mellon’s campus Prototype working on Carnegie Mellon’s campus  Restaurant concierge agent, message filtering agent, etc.  Integration with calendar, location tracking, user profile, etc.  About 40% of messages benefit from context aware filtering and delivery  Quality of context-aware restaurant recommendations led to 15% increase in user satisfaction Additional customization for context-aware enterprise and DoD applications Additional customization for context-aware enterprise and DoD applications

12. Copyright ©2003 Norman Sadeh Ongoing Work e-Wallet security e-Wallet security Learning Learning  Message filtering/delivery preferences  Privacy preferences  Tension between privacy & usability Additional inference capability Additional inference capability  e.g. deriving calendar activities Evaluation, evaluation, evaluation Evaluation, evaluation, evaluation