当前位置:首页 >> >>

Business Knowledge Representation and Reasoning_图文

Research Topic
Business Knowledge Representation and Reasoning

Xingen Wang Oct 26 2005

Why choose this research topic
Why use a rules engine?
The business world is full of cliches about change, how everything changes, how change is the only thing you can depend on. In the technical world, this isn't exactly the case. The current situation is business people decide what the software should do, that is, make the business rules and developers “translate” these rules into code. Since business needs change much faster than software code, there’s the possibility that developers mistranslated the business rules which is hard to detect or software can’t keep up with changing business need.

Why choose this research topic
Separate the business decisions of your executives from the technical decisions of your developers, and to keep those business decisions in a central data store, where they can be managed and altered in real-time (that is, business-time). It's one strategy you might consider. A “rule based engine” is an engine that takes actions according to a set of predefined rules. This perfectly fit in the definition of an expert system. Expert systems were developed by researchers in artificial intelligence during the 1970s and applied commercially throughout the 1980s. Research in expert systems is no longer as popular as it used to be. The DROOL tool used in the CFI project, which is technically a forward chaining expert system, invokes some business method when the IF part of some business rule is satisfied. (http://drools.codehaus.org/)

Introduction
Knowledge representation and reasoning are traditional areas within artificial intelligence. In the modern society they are underlying building blocks in various kinds of information systems and networks. Knowledge representation and reasoning are also central themes in cognitive science and epistemology. Relevant questions include how we know what we know, how we can make useful inferences, and how we can use computers in models and applications of knowledge representation and reasoning. Traditional models have been based on predicate logic, semantic networks and other symbolic representations.

Introduction
What do we want in a representation?
We want a representation to be ? rich enough to express the knowledge needed to solve the problem. ? as close to the problem as possible: compact, natural and maintainable. ? amenable to efficient computation; able to express features of the problem we can exploit for computational gain. ? learnable from data and past experiences. ? able to trade off accuracy and computation time

Introduction
Three views of KR
? KR as semantics. We want to devise logics in which you can state whatever you want, and derive their logical conclusions. Examples: Logics of Bacchus and Halpern ? KR as common-sense reasoning. We want something where you can throw in any knowledge and get out ‘reasonable’ answers. Examples: nonmonotonic reasoning, maximum entropy. ? KR as modeling. We want a symbolic modeling language for ‘natural’ modelling of domains. Examples: logic programming, Bayesian networks.

Status of Knowledge Representation
Current methods of Knowledge Representation (KR) Logic: A way of declaratively representing knowledge. For example: person(Socrates). person(Hillary). forall X [person(X) ---> mortal(X)] Production (Rules) System: The most popular method. e.g. (object, property, value, probability) or (Relation, object1, object2, probability) Networks: A compromise between declarative and procedural schemes. Knowledge is represented in a labeled, directed graph whose nodes represent concepts and entities, while its arcs represent relationships between these entities and concepts. Frames: Much like a semantic network except each node represents prototypical concepts and/or situations. Each node has several property slots whose values may be specified or inherited by default. Object-Oriented: smalltalk, C++, Java State-Space: (S,F,G)

Other KR Paradigms
Procedural Knowledge: Knowledge is encoded in functions/procedures. For example: function Person(X) return boolean is if (X = ``Socrates'') or (X = ``Hillary'') then return true else return false; function Mortal(X) return boolean is return person(X); Decision Trees: Concepts are organized in the form of a tree. Statistical Knowledge: The use of certainty factors, Bayesian Networks, Dempster-Shafer Theory, Fuzzy Logics, ..., etc. Parallel Distributed processing: The use of connectionist models. Subsumption Architectures: Behaviors are encoded (represented) using layers of simple (numeric) finite-state machine elements. Hybrid Schemes: Any representation formalism employing a combination of KR schemes.

Status of Reasoning
Current methods of Reasoning Logical (Deductive) Reasoning: Uncertain reasoning:
Probability Reasoning Bayesian Reasoning D-S Reasoning …

Research Hotspots
Combining expressive knowledge representation formalisms (such as relational and first-order logic) with principled probabilistic and statistical approaches to inference and learning. This combination is needed in order to face the challenge of real-world learning and data mining problems in which the data are complex and heterogeneous.

Research Hotspots
Adaptive approaches of knowledge representation and reasoning. The basic idea is to bring together evidence from various disciplines including computer science, experimental psychology, brain research and cognitive science. Methodological basis lies in probability theory, statistics, artificial neural networks, dynamical systems theory and related disciplines.

Research Hotspots
Contextually in statistical analysis and reasoning Bayesian models of learning and reasoning dynamical systems models of knowledge spatial representations of knowledge analyses of the limitations of logic-based representations and reasoning highly contextual reasoning based on very high-dimensional representations continuous formal systems pattern-based reasoning unsupervised and reinforcement learning models for knowledge acquisition and representation emergent representations based on independent component analysis and self-organizing maps emergence of symbolic representations cognitive models of perceptually grounded reasoning processes

Research Hotspots
knowledge representation and reasoning in non-stationary environments explicit and implicit knowledge internal and external representations models of temporal processes and reasoning subjective and intersubjective representation of time knowledge representation and reasoning in the brain non-symbolic ontologies and adaptive knowledge representation for the web adaptive, dynamical and probabilistic representations of social and societal structures and processes adaptive knowledge representation of industrial processes probabilistic and pattern-based reasoning on financial and economical phenomena emergent and evolutionary representations for creative and design processes

Research Hotspots
Uncertain reasoning formalisms, calculi and methodologies Reasoning with probability, possibility, fuzzy logic, belief functions, argumentation, rough sets, and probability logics Modelling and reasoning using imprecise and indeterminate information, using for instance: Choquet capacities, comparative orderings, convex sets of measures, and interval-valued probabilities Exact, approximate and qualitative uncertain reasoning Nonmonotonic reasoning Multi-agent uncertain reasoning and decision making Decision-theoretic planning and Markov decision process Temporal reasoning and uncertainty Construction of models from elicitation, data mining and knowledge discovery Uncertain reasoning in information retrieval, filtering, fusion, diagnosis, prediction, and situation assessment Practical applications of uncertain reasoning

Thank you!


更多相关标签: