Kein Folientitel

1
Knowledge Technologies 2001 Siemens Automation
and Drive Help Desk A Knowledge Work-Place
with Self-Service Norman Zimmer empolis NA,
Inc. Burlington, MA
2
SIEMENS Automation Drives

• Process Control Systems
• Machinery

3
Distributed Organization
4
Call-Center Pyramid
5
What is CBR ?
Case-Based Reasoning (CBR) is a problem solving
approach, that applies known solutions of past
problems to solve new ones.
Experience is documented as a case. A new
problem is solved by adapting the solution of a
stored case to the new situation.
6
Examples

• A doctor remembers past patient records.
• An advocat argues by precedence.
• An architect reuses designs of existing
  buildings.
• A sales agent explains a new product by referring
  to satisfied customers.
• A service technician remembers a similar defect
  from another machinery.

7
Knowledge-Server Idea
?
!
Knowledge is key to transform Data into
Information
Answers
Questions
Content Base
8
Motivation

• Reuse experience to solve new problems
• Known examples utilize structured data in
  databases
• but in most cases there is a lot of existing
  unstructured information in free text form
• Is it possible to apply the CBR paradigm to such
  text information?

9
Knowledge in Text

• In many areas knowledge is stored as weakly
  structured text
• Frequently Asked Questions
• Documentations
• Manuals
• Notes and Comments
• Customer queries
• Proposals
• and many more ...

10
Knowledge in Text

• Documents contain a lot corporate knowledge
• Documents have specific characteristics
• restricted topic
• mostly free text
• partly structured (chapters, section, ...)
• many documents address the same topic

11
Example FAQ

• FAQ document
• HardwarePC HP DeskJet 870
• Software Windows 95
• QuestionMy new printer crops graphic print
  outs.
• Answerload and install new printer driver

12
Example Dictionary
13
Example Ontology
14
Example Synonyms
15
Example Antonyms
16
Example Query

• Q On my PC the input of a long street name
  causes a crash. The error message is
  Memoryfault.

17
Example Query

• Q On my PC the input of a long street name
  causes a crash. The error message is
  Memoryfault.

18
Example Query and Results

• Q On my PC the input of a long street name
  causes a crash. The error message is
  Memoryfault.
• F1 On Windows 3.1 there is not enough memory
  allocated for the name of the street. This may
  cause the system to go down.
• F2 The PC-Version stores the street name
  incorrectly.
• F3 Typing German characters causes a Sun to
  crash.

19
Example Query and Results

• Q On my PC the input of a long street name
  causes a crash. The error message is
  Memoryfault.
• F1 On Windows 3.1 there is not enough memory
  allocated for the name of the street. This may
  cause the system to go down.
• F2 The PC-Version stores the street name
  incorrectly.
• F3 Typing German characters causes a Sun to
  crash.

20
Analyzing Text

• Create a dictionary of relevant terms
• Create relations and similarities
• Utilize layers of knowledge
• Keywords relevant common terms
• Phrases application specific terms
• Feature Values structured information
• Thesaurus relations among keywords
• Glossary relations among phrases
• Domain Structure e.g. products
• Information Extraction feature values from text

21
Prerequisites

• Availability of appropriate documents
• the more the better (initially)
• extensible
• Semi-automatic construction of dictionaries
• databases, other documents
• Semi-automatic construction of the knowledge
  model
• databases, existing glossaries

22
Ideal

• Many documents electronically available
• HTML, TXT, DOC, PDF, ...
• Clearly distinguished topics
• specific application area
• Documents correspond to cases
• 1 Case 1 Document
• 1 Case 1 Section in a document
• Many users
• customers and technicians via WWW
• in-house teams via Intranet

23
Example Document
Clear topic sub-structure by products specific
vocabulary
24
Knowledge Capture Process
25
Text
26
Ontology
27
SIMATIC Knowledge manager
orengeServer
Knowledge model
Search
Structure Informa-tion about SIMATIC Product
structure
Products Order no. Product name
Dictionary Inform-ationunits Simil- arities
Results
www.ad.siemens.de
Document view
Documents within the customerssupport
informationsystem
28
Analysis of Queries
29
SIMATIC Knowledge Manager
Search in 20.000 FAQs CD-Rom Internet seamless
integration Online since 1998 German English
FAQ Support
30
Call Avoidance Savings
Savings in Thousands
2.5 Million Dollar Savings in 12 Months
31
Measurement

• Number of Calls
• Time to Solve Problems
• Amount of Knowledge
• Coverage
• User Satisfaction
• Cost of Evolution

32
Transforming Information into Value