System and method for implementing a knowledge management system

Abstract

A method and system organize and retrieve information using taxonomies, a document classifier, and an autocontextualizer. Documents (or other knowledge containers) in an organization and retrieval subsystem may be manually or automatically classified into taxonomies. Documents are transformed from clear text into a structured record. Automatically constructed indexes help identify when the structured record is an appropriate response to a query. An automatic term extractor creates a list of terms indicative of the documents' subject matter. A subject matter expert identifies the terms relevant to the taxonomies. A term analysis system assigns the relevant terms to one or more taxonomies, and a suitable algorithm is then used to determine the relatedness between each list of terms and its associated taxonomy. The system then clusters documents for each taxonomy in accordance with the weights ascribed to the terms in the taxonomy's list and a directed acyclic graph (DAG) structure is created.

Description

RELATED APPLICATIONS [0001] This application is a divisional of U.S. application Ser. No. 10 / 610,994 filed Jul. 1, 2003, which is a divisional of U.S. application Ser. No. 09 / 594,083 filed Jun. 15, 2000 (now issued as U.S. Pat. No. 6,711,585), which claims priority under 35 U.S.C. 119(e) from U.S. Provisional Application No. 60 / 139,509, filed Jun. 15, 1999, which applications are incorporated herein by reference.FIELD OF THE INVENTION [0002] This invention relates to systems and methods that facilitate the orderly storage of information and more particularly to a system and method for generating and utilizing knowledge containers for the orderly storage and retrieval of information. BACKGROUND [0003] A key resource of most, if not all, enterprises is knowledge. For example, in a customer service environment, customers expect prompt and correct answers to their information requests. These information requests may relate to problems with products the customer has purchased, or to ques...

AI Technical Summary

Benefits of technology

[0009] The present invention may then be used to aid a researcher or user in quickly identifying relevant documents, in response to an inputted query. It may be appreciated that both a documents content and information added during autocontextualization is available for retrieval in the present invention. Moreover, the present system can retrieve any type of knowledge container, including not only those derived from some kind of document (such as “document” or “question” knowledge containers) but also those that represent people and resources (such as knowledge consumer and product knowledge containers.) In a preferred embodiment, two retrieval techniques may be utilized: multiple-taxonomy browsing and query-based retrieval. In multiple-taxonomy browsing, the user spe

Problems solved by technology

Further complicating the situation is the fact that very few customer service representatives possess the skills necessary to assist customers on more than a limited number of topics.

Unfortunately, providing customer service representatives with the knowledge necessary to adequately serve customers involves time-consuming and expensive training.

Even with training, customer service representatives will inevitably encounter questions for which no reasonable amount of training can prepare them to answer without expert consultation.

The delay endured by the customer as the customer service representative consults with an expert is inconvenient, and often intolerable.

Unfortunately, they are considerably less

Images