Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
1999-10-01
2004-08-24
Kindred, Alford (Department: 2172)
Data processing: database and file management or data structures
Database design
Data structure types
C706S045000, C706S050000
Reexamination Certificate
active
06782391
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates generally to updating a knowledge base, and more particularly, to a method of automatically creating Metadata and automatically updating the Metadata in a knowledge base.
BACKGROUND OF THE INVENTION
Businesses are taking advantage of the Internet and technology to free up customer service agents (CSAs) by deflecting work from their queues and directing users, such as clients and customers, to other self-service information sources like Internet knowledge bases. The data residing in a knowledge base (KB) is often created and indexed by a customer service agent. Customer service agents spend time to categorize and describe the data (a.k.a. Metadata) so that customers can retrieve the information on-line when querying the KB. Metadata is data about data. Metadata describes how and by whom a particular set of data is collected, and how the data is formatted. Metadata is essential for understanding information stored in data warehouses.
Inconsistencies in data categorization and descriptions, as well as data overlap, is likely to occur with many agents creating Metadata for individual responses. Furthermore, if these situations are present in the KB, it is more difficult to satisfy a user's needs in a timely, productive manner. Responses to KB queries are potentially less concise, and/or relevant. This type of on-line user experience may prompt users to forego use of the KB for their next inquiry and revert to customer service agent based communications through the Internet, or by telephoning a call center staffed with customer service agents, thus defeating the original intention of Internet self-service resources and sites.
An attempt to eliminate this problem is for agents to publish their responses. The responses can be transformed into Metadata. Tools for editing, loading, and transforming Metadata are known. These tools generate Metadata based on user input and load into corresponding databases. For example, Silknet's eService '98 gives agents the ability to intentionally “publish” their responses to a KB so users can query the database for that same data. Disadvantageously, this tool does not prevent the inclusion of inconsistent, overlapping Metadata into the knowledge base.
A need exists for a tool to intelligently, automatically produce Metadata and determine its usefulness in the scheme of the existing KB by extracting information such as previous and potential KB content, administrative parameters, and the like, and using this information before publishing agent responses to user inquiries in the KB. A further need exists for a tool which eliminates the need for agents to intervene in the KB content and categorization process by automatically describing and maintaining the knowledge base. Another need exists for knowledge base that can be automatically updated with Metadata which is consistent, concise and useful.
SUMMARY OF THE INVENTION
It is, therefore, an object of the present invention to provide a method and apparatus using a knowledge base that can be updated with Metadata which is consistent, concise and useful.
Another object of the present invention is to update a knowledge base using customer service agent's responses to customer inquires which are consistent, concise and useful.
It is another object of the present invention to provide a method to extract information such as previous and potential knowledge base content, administrative parameters and the like and advantageously eliminate the need for agents to intervene in the knowledge base content and categorization process, thereby preventing the creation of inconsistent, overlapping, Metadata KB entries.
It is yet another object of the present invention to provide a method to reduce additional customer service agent work (i.e., Metadata creation for every customer inquiry response).
It is yet a further object of the present invention to provide a method that automatically organizes Internet self-service resources such as a KB by providing a methodical, consistent technique for describing and maintaining KB data (i.e., Metadata creation).
It is another object of the present invention to provide a method that increases the credibility of KB data by using factors such as agent skill set, expertise levels, etc., and weighting their importance when creating KB Metadata and entries.
It is yet another object of the present invention to provide a method that reduces the time a customer spends on-line by eliminating the need to browse excessive numbers of KB entries by pre-filtering redundant agent responses, and consistently assigning characteristics and/or attributes to KB data.
It is yet another object of the present invention to provide the opportunity to present more accurate and appropriate responses to an on-line customer inquiry by reducing KB data redundancy, and consistently creating Metadata used in on-line KB queries.
According to the present invention, to promote the use of self-service resources and divert potential agent work (i.e., the creation of Metadata for individual inquiry responses), by using an Intelligent Knowledge Base Content Categorizer (IKBCC) is used to provide descriptive, useful, consistent KB Metadata, minimize KB data overlap, and log KB Metadata/CSA responses. For example, the IKBCC is invoked after an agent's response to a customer request is created and quality checked. The IKBCC evaluates the attributes and/or characteristics of a response based on response content, prior KB entries, KB content index, administrative parameters, and/or other factors. If the IKBCC determines that the response is unique in one or more ways from the current KB entries, then a Metadata entry for the response and the response data itself, are written to the KB without the intervention of a human agent. Advantageously, the IKBCC functions as an interface between a customer service agent and the KB so that the KB can be updated with customer service agents responses to customer inquiries which are consistent, concise and useful.
This invention provides a method for improving the quality of Metadata and information resident on an Internet self-service resource such as a KB. It also assists in reducing and/or negating the time CSAs spend to publish their responses to customer inquiries in a KB. The IKBCC accomplishes both these goals by automatically, intelligently, and consistently evaluating the contents of CSA responses to customer requests. It proactively determines the value of adding a response to the existing database, and methodically produces Metadata to describe each new KB entry. The IKBCC uses an algorithm that factors in variables (such as KB data, CSA information, administrative parameters, etc.), to evaluate whether a KB entry already exists or should be added. It then determines the nature of the Metadata to describe the added entries. This invention works as an integral part of an overall Internet self-service offering. And its method of indexing agent responses provides end users with a KB that allows them timelier, more relevant query feedback, by categorizing and organizing the data within an available Internet self-service resource.
These and other objects of the present invention are achieved by a computer-implemented method of automatically adding data to a database using human agent responses to questions including receiving a question and routing the question to a human agent. Using the human agent's response, it is determined whether to add the response to the database, and if the determining step is positive then updating the database with the response and if the determining step is negative then rejecting the response.
The foregoing and other objects of the invention are achieved by a computer system including a processor and a memory coupled to the processor, the memory having stored therein sequences of instructions, which, when executed by the processor, causes the processor, after receiving a response to a question from a human agent, to perform the steps of using the human agent's re
Kindred Alford
Lowe Hauptman & Gilman & Berner LLP
NCR Corporation
LandOfFree
Intelligent knowledge base content categorizer (IKBCC) does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Intelligent knowledge base content categorizer (IKBCC), we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Intelligent knowledge base content categorizer (IKBCC) will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3343380