ABSTRACT
Currently, few organizations have a systematic process for capturing
knowledge, as distinct from data. The authors illustrate how a large
oil and gas service company uses knowledge-engineering processes to capture,
store, and deploy drilling-optimization knowledge.
In recent years, knowledge management has referred to efforts to capture, store, and deploy knowledge using a combination of information technology and business processes. More specifically, organizations aim to acquire knowledge from valued individuals and to analyze business activities to learn from successes and failures. Such captured knowledge must then be made available throughout the organization in a timely manner.
In terms of technology, most current knowledge management activities rely on database and Internet systems. If knowledge is stored explicitly at all, it is typically in databases either as simple tables (for example, relational databases) or semistructured text (as in Lotus Notes). The use of sophisticated knowledge representation systems such as Classic, Loom, or G2 is rare. Also, few organizations have a systematic process for capturing information.
We believe that current knowledge management practice significantly
under-utilizes knowledge-engineering technology, despite recent efforts
to promote its use. In this article, we focus on two knowledge-engineering
processes:
To demonstrate the usefulness of these processes, we present a case
study in which the drilling optimization group of a large oil and gas service
company uses knowledge-engineering practices to support the three facets
of the knowledge management task:
Derek Sleeman, Zhi Luo, Peter Andrews & Pat Jones (2001) What insights can be obtained from Temporal Physiological Data-sets collected during Intensive Care for Head-Injury patients? Workshop on Computers in Anaesthesia & Intensive Care: Knowledge-Based Information Management at AIME-01 (Cascais, Portugal)
ABSTRACT
At the 1999 AIME Conference [1] we reported a decision tree study on
a subset of data, including time series physiological data, admissions
characteristics, and outcome after traumatic head injury. That study
analysed total duration for which patients had, for example, raised Intracranial
Pressure, but it did not consider temporal relationships between various
physiological and clinical events. In this study, we have addressed
that issue in a number of ways. Firstly, by asking clinicians to
make predictions of expected outcome based on complete physiological and
clinical data. Secondly, repeating the exercise with a reduced (more compact)
representation for the physiological data. Thirdly, patterns were generated,
including "adjacent" physiological parameters and clinicians were asked
if they are likely/very unlikely to cause a particular major physiological
event or outcome. Finally, we implemented a module to test patterns
of the form:
IF X happens then Y will happen between T1-T2
against patient time-series data. Results of all these studies
have so far not been conclusive; more analyses particularly with the temporal
patterns are currently in progress.
SIMON WHITE, DEREK SLEEMAN (2001). A Grammar-Driven Knowledge Acquisition Tool that incorporates Constraint Propagation. KCAP-01 Conference, Victoria, Canada (October 2001). ACM Press, pp187 – 193.
Abstract To acquire knowledge that is fit for a specific
purpose, it is very desirable to have a structured, declarative expression
of the knowledge that is needed. This paper introduces a stand-alone knowledge
acquisition tool, called COCKATOO (Constraint-Capable Knowledge Acquisition
Tool), which uses constraint technology to specify the knowledge it requires.
The language in which these specifications are given is based on the meta-language
notation of context-free grammars. However, we also took the opportunity
to build a tool that is both more flexible and powerful by augmenting context-free
grammars with the expressiveness of constraints. COCKATOO was implemented
using the SCREAMER+ declarative constraints package.
DEREK SLEEMAN (2001) Knowledge Technologies: A ReUse Perspective. Research and Development in Intelligent Systems XVIII (Proceedings of ES 2001), BCS Conference Series, Springer-Verlag, 2001, pp 3-6.
Abstract In 2000 the EPSRC funded an Interdisciplinary
Research Collaboration (IRC) in Advanced Knowledge Technologies for the
period 2000-2006, which involves 5 UK Universities: Aberdeen, Edinburgh,
OU, Sheffield & Southampton. The project seeks to provide an intellectual
underpinning for much of eCommerce, and at the same time it is contributing
to the definition & realization of the Semantic Web. Six grand challenges
have been identified, namely: Knowledge Acquisition, Modelling, Use/ReUse,
Retrieval, Knowledge Publishing, & Maintenance. Considerable effort
is being expended to ensure that the
different knowledge sources can inter-operate. Additionally, several
industrial test beds should ensure that the group’s earlier & new technologies
are integrated; these test beds are in the service & manufacturing
sectors, and AKT is also applying these techniques to the Consortium’s
own information management. In the talk I plan to review each of the above
activities, but will focus on ReUse (a holy grail for KBS Research). I
will give an overview of what has been achieved to date, & will discuss
several current projects in this sub-area.
A. HAMEED, D. SLEEMAN & A. PREECE (2001). Detecting Mismatches Among Experts' Ontologies Acquired through Knowledge Elicitation. Research and Development in Intelligent Systems XVIII (Proceedings of ES 2001), BCS Conference Series, Springer-Verlag, 2001, pp 9-22.
Abstract We have constructed a set of ontologies modelled on
conceptual structures elicited from several domain experts. Protocols were
collected from various experts who advise on the selection/ specification
and purchase of PCs. These protocols were analysed from the perspective
of both the processes and
the domain knowledge to reflect each expert's inherent conceptualisation
of the domain. We are particularly interested in analysing discrepancies
within and among such experts' ontologies, and have identified a range
of ontology mismatches. A systematic approach to the analysis has been
developed; subsequently
we shall develop software tools to support this process.
A. MCQUATT, D. SLEEMAN, P. J. D. ANDREWS, V. CORRUBLE, P. A. JONES (2001). Discussing Anomalous Situations using Decision Trees: A Head Injury Case Study. Methods of Information in Medicine 2001, pp 373-379.
Abstract
Objectives: Predicting the outcome of seriously ill patients
is a challenging problem for clinicians.
Methods: One alternative to clinical trials is to analyse existing
patient data in an attempt to predict the several outcomes, and to suggest
therapies. In this paper we use decision tree techniques to predict
the outcome of head injury patients. The work is based on patient
data from the Edinburgh Royal Infirmary which contains both background
(demographic) data and temporal (physiological) data.
Results: The focus of this paper is the discussion of the anomalous
cases in the decision trees with the domain experts (the clinicians).
Conclusions: These analyses led to the detection of several
situations where both the data analysis and patient data collection should
be enhanced, which in turn should lead to improved patient care.