Browse Prior Art Database

Business Method to Improve Problem Diagnosis in Current Systems Using a Combination of XML and VoiceXML

IP.com Disclosure Number: IPCOM000014964D
Original Publication Date: 2002-Jan-01
Included in the Prior Art Database: 2003-Jun-20
Document File: 2 page(s) / 45K

Publishing Venue

IBM

Abstract

Business Method to Improve Problem Diagnosis in Current Systems Using a Combination of XML and VoiceXML The current systems for problem diagnosis use's different levels of staff (Level 1, Level 2 etc.) for problem diagnosis and the appropriate call screening and routing, which often leads to inefficiencies in the system due to overstaffing, missed diagnosis, inaccurate routing etc. Staff hiring, retention and training involves high cost. Moreover, people typically acquire expertise in specific areas which means that handover is necessary between staff for problems not related to one's area of expertise. It is generally the case, however, that a significant percentage of the reported problems recur frequently and have been seen before. The task of identifying and diagnosing these is simple and can easily be automated. However, a lot of investment has been made in voice-based systems that need to be leveraged. Moreover, customers often want to describe their problem via speech (doesn't matter if the other end is a machine). To solve this problem, proposed is a XML+VoiceXML based system to promote efficiency by identifying and diagnosing the most frequently occurring problems and appropriately routing problems to the correct help in other cases.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 54% of the total text.

Page 1 of 2

Business Method to Improve Problem Diagnosis in Current Systems Using a

Combination of XML and VoiceXML

The current systems for problem diagnosis use's different levels of staff (Level 1, Level 2 etc.) for problem diagnosis and the appropriate call screening and routing, which often leads to inefficiencies in the system due to overstaffing, missed diagnosis, inaccurate routing etc. Staff hiring, retention and training involves high cost. Moreover, people typically acquire expertise in specific areas which means that handover is necessary between staff for problems not related to one's area of expertise. It is generally the case, however, that a significant percentage of the reported problems recur frequently and have been seen before. The task of identifying and diagnosing these is simple and can easily be automated. However, a lot of investment has been made in voice-based systems that need to be leveraged. Moreover, customers often want to describe their problem via speech (doesn't matter if the other end is a machine).

To solve this problem, proposed is a XML+VoiceXML based system to promote efficiency by identifying and diagnosing the most frequently occurring problems and appropriately routing problems to the correct help in other cases.

When a call comes in, speech recognition is used along with DOM-applications to create
a VoiceXML transformation representing the exchange and also an XML representation of the customer problem. The "most frequently occurrin...