knowledge management: a cbr perspective
DESCRIPTION
Knowledge Management: A CBR Perspective. Sources: David W. Aha My own Thomas H. Davenport, Laurence Prusak, 1998. The Beginning: The Apollo 13 Situation http://www.youtube.com/watch?v=nEl0NsYn1fU. The oxygen tanks had originally been designed to run off the 28 volt DC - PowerPoint PPT PresentationTRANSCRIPT
Knowledge Management: A CBR Perspective
Sources:
• David W. Aha• My own• Thomas H. Davenport, Laurence Prusak, 1998
The Beginning: The Apollo 13 Situationhttp://www.youtube.com/watch?v=nEl0NsYn1fU
• The oxygen tanks had originally been designed to run off the 28 volt DC
• The tanks were redesigned to also run off the 65 volt DC
The Changing Game
The New EconomicsManufacturing ServiceTangible IntangibleConsumable InconsumableStructural Intellectual
Tobin’s Q ratio company’s stock market value / value of its physical assets
Is increasing dramatically. What does this mean?
Increasing importance of intellectual capital in the United States (Barr & Magaldi, 1996)
Knowledge Management (KM)
An increasingly important new business movement that promotes the creation, sharing, & leveraging of knowledge
within an organization to maximize business results.
Effective tools to capture, leverage & reuse knowledge
Technology
Develop a culturefor knowledge sharing
Organizational DynamicsNeeds
Financial constraintsLoss of organizational knowledge
Needs
Problems:
Knowledge Management: Issues
• Technical and Business Expertise:ProficienciesKnow-HowSkills
• Work Practice Execution:ProcessesMethodologiesPracticesLessons learned
Why Knowledge Management?
• Leverages Core Business Competence
• Accelerates Innovation (Time to Market)
• Improves Cycle Times (Market to Collection)
• Improves Decision Making
• Strengthens Organizational Commitment
• Builds sustainable differentiation
CBR: The Knowledge Management Plunge
“Case-based reasoning programs have been shown to bring about marked improvements in customer service.”
- Thomas H. Davenport, Laurence Prusak, 1998 - Working Knowledge: How Organizations Manage What They Know
KM
CBRWorks
eGain eService Enterprise (E3)
KM Project Domains: CBR Applicable? (KM World, 1/99, Dan Holtshouse, Xerox)
1. Sharing knowledge and best practices2. Instilling responsibility for knowledge sharing3. Capturing and reusing past experiences4. Embedding knowledge (products/services/processes)5. Producing knowledge as a product 6. Driving knowledge generation for innovation7. Mapping networks of experts8. Building/mining customer knowledge bases9. Understanding/mining customer knowledge bases10. Leveraging intellectual assets.
KM Domains/Tasks CBR Applicable?YesNoYesYes Yes No
YesNoYes
No
Recent Events Related to KM/CBR
1999 Summer Workshops:– AAAI: Exploring the Synergies between KM and CBR (Co-chair)– ICCBR: Practical CBR Strategies for Building/Maintaining Corporate Memories– ICCBR: Integration of CBR in Business Processes– IJCAI: Automating the Construction of CBRs
Special issues:– Human-Computer Studies (1999)– Knowledge-based Systems (2000)
AAAI 2000 Spring Symposium:– Bringing Knowledge to Business Processes
2003 German CBR Workshops is now German KM Workshop
1999 AAAI KM/CBR Workshop~45 attendees: Siemens, Schlumberger, Motorola, NEC, British
Airways, General Motors, Boeing, Ford Motor Company, World Bank
Goals:1. Explain KM issues to CBR researchers2. Report on recent CBR approaches for KM tasks3. Share cautions, knowledge, & experiences
Some observations:1. Embedded/integrated in knowledge processes2. Benefits of semi-structured case representations3. Interactive (“conversational”) systems
Limitations of CBR for KM(from the 1999 AAAI KM/CBR Workshop)
1. Main limitation is time and effort? (Wess/Haley)
2. Limitations from working with simple representations (Haley)– Becoming less problematic (e.g., with development of textual CBR)
3. Rule-based integrations– Suffer from old problems of rule acquisition– But KM problem-solving techniques are combating this (Studer)
4. More intuitive case authoring capabilities
5. Tools for working with heterogeneous data sources
Panel: Lessons & Suggested Directions
CBR Roles:– Accumulate, extend, preserve, distribute, reuse corporate knowledge– Extracting tacit knowledge– Customer relationship management
Lessons & Observations:– Integrate CBR with KM tasks & task models– Integrate case retrieval with presentation with tools/workplaces– Integrate case construction/indexing with work product development– Need more advanced (automated) case authoring tools– Must consider effects on user groups, time, organizational impact– CBR not a complete KM solution
Experience Management vs CBR
Experience Management
CBR
(Organization)
(IDSS)2. Reuse3. Revise
4. Retain
Case Library
1. RetrieveBackground Knowledge
Experience base
Reuse-related
knowledge
Problem acquisition
Experience evaluation and retrieval
Experience adaptation
Experience presentation
Complex problem solving
Developm
ent and M
anagement
Methodologies
BO
OK
Relating KM with AI
AI
Knowledge-BasedSystems
HumanFactors KM Business
Processing
CCBR
EXTERNAL MONITORING
AlertsSpiders
Workflow
Scheduling
CollaborationSuspenses
Records Management
Document Management
OA tools
Library catalog
Online databases
E-journals
How-to guides
Document Delivery Service
Bulletin boards
Buckets
Profiles
MIS
INFORMATION SOURCES
WORKSPACE
PERSONAL PORTAL
AFRL Proposed KM Environment
(multi?) impersonal
Personalization
Semantic Web Ontologies
DS1
DS2
DS3
Distributeddata sources
AssistantAgent
Case Repository
Causal ModelCurrent Problem
User Ontologies
Personal Portal/Workspace
InformationSources
NEWS
BULLETINBOARDS
SUSPENSES/TASKS RESEARCH ASSISTANT
CALENDAR/SCHEDULING
4 5 6 81 2 3 7
WORKSPACE
WHO’SWHO
GUIDES
FAVORITEWEB SITES
Microsoft Word.lnk Micro sof t Pow erPo int.ln k Micros oft Excel.lnk
Individualized Portal
Information Domains
Data Systems
Virtual Library
BucketsFinance
Personnel
A B C D
Executive Information System
Out-of-Family Disposition (OOFD) Process
NASA-Kennedy Space Center: Shuttle Processing Directorate
KM expertise
CBR expertise
Topic: Performing project tasks outside range of expertise• Lack of task familiarity
Motivations: Downsizing, employee loss, technology paceResources: Interim problem reports
• Standardized text documents for reporting problems/solutions• Given: 12 of these reports
Pre-flight, launch, landing, recovery
Prof. I. Becerra-Fernandez
Another example: legal constraints
OOFD: Problem Categorization (Ontology)
Prompt Problem
Computer
Electrical
Materials
Mechanical
Data Drop Out
FCMS GMT Discrepancy
PCM 3 Shows up in PCM 2
Micro-switch Malfunctioning
Unexplained Power Drops
Helium ISO Valves
Backup HGDS
Seal Port Dynatube
Catch Bottle Relief Valve
Stress Corrosion Cracking
Debris Detected in Stiffener ring
Cracked A8U Panel
2 2.1 2.2 2.3 2.4 2.5
12
4
7
11 11.1 11.2 11.3 11.4 11.5 11.6
1
3
5
6
10
8
9
1.1 1.2
10.1 10.2 10.3
8.1 8.2 8.3
9.1 9.2
Has this data alreadybeen gathered? If so,
WHERE? NO, needto gather data
NO, neednew mission
ScienceDataNeed
YES, here is the DATA! YES, recommend thisOBSERVATORY!
Science Mission Parameters
Science Mission Assistant and Research Tool (SMART)
Intelligent DataProspector (IDP) Intelligent Resource
Prospector (IRP)
Design Assistant(IMDA)
Intelligent Mission
Can anexisting resource
obtain the data for me?If so,
WHAT?
I would like toformulate
a new mission…HOW?
Example KM Aplication: SMART KM Portal
SMART: Science Mission Assistant & Research ToolCategorization: An interactive, web-based tool suitePurpose: Reduce time/cost required to define new science initiatives
Uncertainty
SMART is Architected as a Web Portal
SMART User
WebBrowser
http://smart.gsfc.nasa.gov
SMART
Intelligent Data Prospector Find data sets
Intelligent Resource Prospector Find an observatory
Intelligent Mission Design Asst Design a science mission
http://smart.gsfc.nasa.gov/irp/
Browse Observatory Knowledge Base Map
TreeObservatory Lists
Search Observatory Knowledge BaseWord/Phrase Search Interactive Dialog
DiscussionsExperts
SMARTIntelligent Resource Prospector
http://smart.gsfc.nasa.gov/imda/
Browse Mission Knowledge Base MapTreeMission Lists
Search Mission Knowledge BaseWord/Phrase Search Interactive Dialog
DiscussionsExperts
Design a Mission
SMARTIntelligent Mission Design Asst
SMARTConcept Map Viewer: Observatories
SMARTHierarchical DirectoryViewer
SMARTDatabase Views
SMARTConversational CBRQuestion/ResponseInterface
SMARTCollaborativeDiscussions Interface
SMART IMDADesign a Mission
Create/Edit a MissionValidate Design
Power Design AdvisorThermal Design AdvisorCommunications
Design Advisor…
InvokeDesign
ValidationAgent
(applet)
(serverDBaccess)
(applet)
(KM toolservice)
(KM toolservice)
(expertsystems)
Searching for Missions Using CCBR
SMARTConversational Mission Search Engine
Describe what you are looking for:“I’m looking for astronomy missions in low-Earth orbit.”
Ranked questions:Score Answer Name Title
“X-ray” Q17 What portion of the spectrum is observed?60 Q7 What launch vehicle?50 Q32 What mission phase?20 Q23 Low or high inclination orbit?10 Q41 Cryogenically-cooled instrument?Ranked cases:Score Name Title90 XTE X-Ray Timing Explorer90 AXAF Chandra X-Ray Observatory30 GRO Gamma Ray Observatory30 EUVE Extreme Ultra-Violet Explorer
Question: Q17Title: What portion of the spectrum is observed?Description: What portion of the electro-magnetic spectrum are you interested in?Select your answer:
Visible light Infra-red Ultra-violet Microwave X-Ray Radiowave Gamma Ray
SMART Browse/Search Process
ConceptMaps
Conceptof
Interest
Form/DB
Query
Web-basedDocument
Library
ExternalKnowledge
Sources
CCBR
Objectof
Interest
Document of
Interest
Select
Query Result
URL
Find
Word docPresentationSpreadsheetBookmark
Browse KB
Browse HierarchySearch Keywords
Search KB Objects
Search KB Objects
Select
URL
URL
URL
URL
URL
URL
URL
SMART Users have a variety of browse and search tools to find documents, objects, and external knowledge sources.
SMART Knowledge Base Objects
XMLObjects
RDB
CaseBases
FactBases
Cmaps CmapTool
CCBRTool
KnowledgeAgents
VisualXML
Editor
Forms/DBInterface
SpreadsheetInterface
Wizards
Case entry/search
Analysis
e.g. Cmap Search Agent Design Validation Agent
Cmapedit/view
Knowledgecapture/view
Knowledgecapture/view
Knowledgecapture
SMART uses XML as the standard representation of knowledge base objects.
Lessons LearnedKeywords: Philippines, evacuation, disaster relief, c2, NEO, Fiery Vigil, etc.
Observation: Assignment of air traffic controllers to augment host country controllers was critical to safe evacuation airfield operation.
Discussion: The rapid build-up of military flight operations…overloaded the civilian host nation controllers. Military controllers maintained 24 hour operations. ...
Lesson Learned: Military air traffic controllers are required whenever a civilian airport is transformed into an intensive military operating area for contingency operations.
Recommended Action: Ensure controllers and liaison teams are part of the evacuation package, and establish early liaison with host nation to coordinate an agreement on operational procedures.
What
How
When
Joint Unified Lessons Learned System (JULLS)
Database: 908 “scrubbed” lessons from the CINC’s (1991-)– Unclassified subset: 150 lessons (Armed Forces Staff College)
• 33 relate to NEOs
Lesson Format: 43 attributes– e.g., ID Number, submitting command, subject, date– Unified Joint Task List number– Content attributes: All in text format
6 Keywords6 Observation6 Discussion6 Lesson learned6 Recommended action
Some Lessons Learned Centers/SystemsAir Force o Air Force Automated Lessons Learned Capture and Retrieval System o Air Force Center for Knowledge Sharing Lessons Learned o Air Combat Command Center for Lessons Learned o Automated Lessons Learned Collection & Retrieval SystemArmy o Center for Army Lessons Learned (CALL) o SARDA: Contracting Lessons Learned o US Army Europe - Lessons Learned SystemCoast Guard o Coast Guard Universal Lessons LearnedJoint Forces o JCLL: Joint Center for Lessons LearnedMarine Corps o Marine Corps Lessons Learned SystemNavy o NDC: Navy Doctrine Command Lessons Learned System o NAWCAD: Navy Combined Automated Lessons Learned o NAVFAC: Naval Facilities Engineering Command Lessons Learned System Government (non-military) o NASA Lessons Learned Information System o International Safety Lessons Learned Information System o NASA-Goddard: RECALL: Reusable Experience with CBR for Automating Lessons Learned) o NIST: Best Practices Hyperlinks o DoE: US Department of Energy Lessons Learned Other o Canadian Army Lessons Learned Centre o United Nations: UN Lessons Learned in Peacekeeping Operations
Lessons Learned Repositories: Functionality
Center forLessons Learned
Documented Lessons
Decision-SupportTool
RetrievalTool
Interface
LessonsLearned
Repository
Lessons Learned System
Search queries Relevantlessons
Lessons Learned Systems: Unrealistic Assumptions
The decision maker1. has time to search for lessons,2. knows where to search for lessons,3. knows how to search for lessons, and4. knows how to interpret retrieved lessons for their
current decision-making context.
Decision SupportTool
UserInterface
Active Lessons Learned Repositories
Center forLessons Learned
Documented Lessons
RetrievalTool
Interface
LessonsLearned
Repository
Lessons Learned System
LL Agent: (CBR)• Relevance
Assessment• Retrieval• Interpretation
Search queries Relevantlessons
Issues for Active Lessons Learned
Documented Lessons
LL Agent(CBR)User
Case Library
Case extraction
Decision SupportTool
Decision-Making Process
1. Case extraction methods2. Case representation3. Choice of decision support tool4. Embedded LL agent behavior
Case Extraction Methods
Textual CBR Tasks:– Case retrieval (FAQ analysis, travel planning) (Lenz et al. 1998)– Extract/highlight relevant portions of case text (Daniels, 1998)– Assigning indices to case texts (Bruninghaus & Ashley, 1999)– Reasoning with cases as text (Weber et al., 2000?)
Textual CBR: • Involves CBR applications where cases are available as texts.• Retrieve, highlight, assign indices to or reason about textual
cases automatically.• Apply CBR knowledge representation frameworks, application-
specific, problem-solving knowledge and other knowledge.
Textual CBR Info Sources
1. Meaning of terms in documents (e.g., thesauri, glossaries)2. Document structure3. Annotated excerpts and summaries4. Citation information5. Linguistic knowledge (i.e., to identify phrases, negation, etc.)6. Frame-based structures for case representation (e.g.,
CMaps)7. Abstraction hierarchies (i.e., relating indices to abstract
concepts)8. Contextual relationship of words (i.e., in manually-classified
texts)
4. Embedded LL Behavior: A Critiquing Agent
USER
LessonsLearned
Case LibraryAutonomous LL Agent
(CBR Engine)
Decision Support Tool
Objects, Operators
Alerts,Recommendations
IndexSimilarity Assessment
Action
Case TypeTask Decompositiontask it decomposesInteractiveTask Subtasks
Lesson Learnedlesson’s conditionsAutomatedArbitrary modifications to System’s objects
Objects := Apply(Op,Objects)Operator selection
Lessons Learned: NEO Critiquing Example
Compose an Intermediate Stage Base
Tasks
Scenario:• 50 miles from ISB #1• 30 miles from ISB #2
• Commercial airfield
Resources:• Transport vehicles
• …• Joint Air Command
• Military air traffic controller• ...
Objects:1. Planning tasks2. Resources3. Assignments4. Task relations5. Scenario
Coordinatewith localsecurity forces
Coordinate withairfield traffic controllers
...
Lesson Learned #13167-92740:• Index: Coordinate w/ traffic controllers• Lesson: If ISB is a commercial airfield,
then assign military air traffic controllers to the evacuation package
Transport militaryair traffic controller to ISB
Process-Oriented CBR(“It’s the Process, Stupid!”)
Most KM tasks are performed in the context of a well-defined (e.g., business) process, and any techniques
designed to support KM must be embedded in this process
KM examples (many):• Enterprise resource planning (O’Leary)• Project process (Maurer & Holz)
CBR examples (few):•Leake et al.: Feasibility assessment in design process•Moussavi, Shimazu: Cases represent processes•Reddy & Munoz-Avila: Project Planning
Distinguishing KM from Data Mining
KDD Focus:• Large databases• Autonomous pattern recognition
Knowledge Discovery from Databases Process:
Database Acquisition
Data Warehousing
Data Cleansing
Data Mining
Data Maintenance
KM Focus:• Capturing organizational dynamics processes• Interaction (i.e., decision support)
KM/CBR: Possible Future Directions
1. Applications– e-Commerce– Decision support systems
• Personalized– Knowledge discovery for databases?
• Yet KDD stresses need for many automated tasks
2. Multimodal systems– e.g., Shimazu: Audio tapes of customer dialogues– Information gathering– Learning assistants
3. Process-focused emphases:– Retrieval, adaptation, and composition of processes
Summary
• There is a real need for Knowledge Management
• Out-of-Family Disposition (OOFD) Process as a particular kind of KM problem
• Studied a concrete application: SMART (NASA)
• Lesson Learned
• Future research applications