Case-Based Reasoning: An Implemented Methodology
Pradeep Raman · 1995
Case Based Reasoning (CBR) is the process by which a computer system solves a given problem based on the knowledge gained from solving precedents in the past. It is a popular AI technique in the area of customer service or HelpDesks, whereby a system that uses CBR as its problem solving approach is utilized to solve most of the commonly occurring customer problems or questions. While the implementation techniques may vary, most CBR systems include the following five steps in some form or other: Representation where problem storage is handled, Retrieval where the closest-matching precedent is identified, Adaptation where a solution is generated from the retrieved problem, Validation where the accuracy of the solution is verified, and finally Update where the database is modified or updated with the information gained from this problem solving process. This paper details the various implementation techniques for these five steps in the CBR process, while focusing on the methods used by one particular problem-solving application namely _Smart USA_. This system solves customer problems by filtering their problem descriptions through an alias table to handle abbreviations and non-key words and then matching the remaining keywords with those in the case database. It is an effective and user-friendly solution which successfully handles different descriptions of the same problem and allows for the case base to be built in free-formatted text. Major companies such as Compaq and NEC utilize a CBR based automated system to serve their customer service needs. These systems have played a significant role in reducing the overhead and the response times involved in the customer service departments of these organizations.