Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

18
C a r n e g i e M e l l 1 Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context Kathleen Yang [email protected] Neha Pattan [email protected] Alejandro Rivera [email protected] Martin Griss [email protected]

description

Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context. Kathleen Yang [email protected] Neha Pattan [email protected] Alejandro Rivera [email protected] Martin Griss [email protected]. Problem Vision Related Work Solution Architecture - PowerPoint PPT Presentation

Transcript of Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Page 1: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

1

Business Meeting Organizer

A Multi-Agent Meeting Scheduler using Mobile ContextKathleen Yang

[email protected]

Neha Pattan [email protected]

Alejandro Rivera [email protected]

Martin Griss [email protected]

Page 2: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Agenda

•Problem•Vision•Related Work•Solution•Architecture•Implementation•Experimental results•Conclusion•Q&A

2

Page 3: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

The problem…

Organizing meetings with multiple people

•When to meet?•Where to meet?•Who must attend the meeting?

•When to reschedule?

3

Page 4: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Vision

Business Meeting Organizer

•Schedules meetings•Co-ordinates common time slots and venues

•Tracks context of attendees

•Reschedules meetings4

Page 5: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Related Work

• Lin J.H., J. Wu and S.L. Lai “Ameetzer”• Agent based meeting modeling to automate the task of scheduling meetings

• Chen, H. “An intelligent broker architecture for context aware systems”

• Broker architecture to maintain a shared model of the context

• Haynes T., S. Sen, N. Arora and R. Nadela.: “An automated meeting scheduling system that utilizes user preferences”

• Adopting user preferences in meeting scheduling systems

• Griss, M., Letsinger, R., Cowan D., Vanhilst, M. and R. Kessler: “CoolAgent: Intelligent Digital Assistants for Mobile”

• Adaptation of multi agent based meeting schedulers to changing environment

• Crawford, E. and M. Veloso: “Opportunities for learning in multi-agent meeting scheduling”

5

Page 6: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Goals

• Mobile client that interacts with end user

• Each user owns a software agent that acts like the user’s Personal Secretary

• Agents communicate and negotiate meetings on behalf of their owners

• Agent is responsible for tracking owner and notifying other secretaries

• Agent has access to owner’s personal data, calendar and contacts

• Agent executes as per owner’s preferences

6

Page 7: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Business Meeting Organizer

•Multi agent based solution •Architecture•Implementation

7

Page 8: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Solution

Agent NegotiationUser

Agent A

User

Agent B

Proposal

Negotiation

Confirmation

A B

8

Page 9: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Architecture (1/2)

Agent

Behaviors

HTTP Server Behavior 1

Calendar Contacts Preferences

Behavior 2 SMS Sender

Services

HTTP SMS

InternetInternet

9

Page 10: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Architecture (2/2)

10

Page 11: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Implementation (1/2)

•Multi-agent environment•Privacy maintained through strict rules•Based on user preferences•Integration of location

–Computes the time to travel between meetings

–Agrees to a meeting only if the time to travel is less than available time between meetings: both before and after proposed meeting

–Sends a reminder on time to user to start travelling to next meeting

11

Page 12: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Implementation (2/2)

•Details about meeting reminder– Agent queries for user’s location every 5 minutes

– Client application on user’s cell phone sends an update to the agent, consisting of GPS co-ordinates

– Agent tracks most recent location of user– Agent computes time to travel to next meeting– Agent sends a reminder 10 minutes before the time when user should start travelling to next meeting

12

Page 13: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

Experimental Results

•Time Consumption•Calendar Privacy•Context Awareness

13

Page 14: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

14

Time Consumption Comparison

14

Tools Negotiation time (minutes)

Request pending time (minutes)

Meeting #1 BMO 1 0 Meeting #2 Google

calendar2 0

Meeting #3 Email 7 50 Meeting #4 Telephone 11 0 Meeting #5 Face-to-

face5 0

Four Participants

Page 15: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

15

Calendar Privacy Comparison

15

Tools Calendar visible to others

Meeting #1 BMO No Meeting #2 Google

calendarYes

Meeting #3 Email No Meeting #4 Telephone No Meeting #5 Face-to-face No

Four Participants

Page 16: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

16

Context Awareness Comparison

16

Tools Location Calendar

Meeting #1

BMO Continuous Continuous

Meeting #2

Google calendar

No Continuous

Meeting #3

Email One shot One shot

Meeting #4

Telephone One shot One shot

Meeting #5

Face-to-face

One shot One shot

Four Participants

Page 17: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

17

Conclusion

•Time spent using BMO is a fraction of that using manual techniques like email and phone calls

•Manual techniques do not scale well for meetings with several attendees, BMO does!

•BMO scores over other techniques in terms of–Efficiency–Privacy–Context Awareness

Page 18: Business Meeting Organizer A Multi-Agent Meeting Scheduler using Mobile Context

Carnegie Mellon

18

Q & A