A Proposal to Combine Probabilistic Reasoning with Case-Based Retrieval for Software Troubleshooting
نویسنده
چکیده
Analysis of a real case of software troubleshooting made it clear that probabilistic models, or Bayesian networks are suitable for modeling software troubleshooting processes in today’s computing environments. As a way to support software troubleshooting by reusing skillful support engineers’ expertise, I propose to use Bayesian networks and probabilistic reasoning for case-based retrieval. The outline of query reformulation using Bayesian network is presented.
منابع مشابه
Case-Based Troubleshooting Knowledge Management
Lack of troubleshooting knowledge support combined with the time pressure to perform can adversely affect the performance on unplanned maintenance tasks. We propose that a knowledge management (KM) perspective should used to support unplanned maintenance tasks. The KM approach explicitly supports the continuous processes of creation, collection, organization, storage, and delivery of troublesho...
متن کاملInformation Retrieval Boosted by Category for Troubleshooting Search System
Troubleshooting search system aims at extracting relevant information to solve the problem at hand. It is often the case that documents in troubleshooting system includes an abundant amount of domain-speci c categories. However, the useful information about the domain-speci c categories, such as relationship between words and categories and relationship between categories, is not fully utilized...
متن کاملOntology Based Information Retrieval: an application to automotive diagnosis
This article describes a real-world semantic information retrieval tool for automotive diagnosis. Troubleshooting documents have always been popular within car workshops / manufacturers as a simple and direct way to capitalize knowledge on the one hand and to access repair information on the other hand. However, with more and more complex vehicle architectures, troubleshooting bases have grown ...
متن کاملValidated Retrieval in Case-Based Reasoning
We combine simple retrieval with domain-specific validation of retrieved cases to produce a useful practical tool for case-based reasoning. Based on 200 real-world cases, we retrieve between three and six cases over a wide range of new problems. This represents a selectivity ranging from 1.5% to 3%, compared to an average selectivity of only 11% from simple retrieval alone.
متن کاملLoad-Frequency Control: a GA based Bayesian Networks Multi-agent System
Bayesian Networks (BN) provides a robust probabilistic method of reasoning under uncertainty. They have been successfully applied in a variety of real-world tasks but they have received little attention in the area of load-frequency control (LFC). In practice, LFC systems use proportional-integral controllers. However since these controllers are designed using a linear model, the nonlinearities...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1998