Top Banner
Industry Telecommunications Objective Radically increase the performance of the inbound contact centre by matching each caller request to the agent with the best expertise; based on the agent’s personal knowledge and past experiences. Approach Instead of the skills-based approach that is so typical for call centres, the approach was based on the agent’s personal knowledge of that specific request, captured from previous calls. A beneficial side effect; this method eliminates the need to manually update every agent’s HR/ skills profile every time they learn new skills. IT Matters Learn any language, directly from a client’s call centre data Autonomous learning and reasoning, which runs on a customised plug and play HPC appliance Leverage the Loop Q platform also with self-learning cognitive S/W robots Cognitively-retrofit all your legacy systems with a single platform End-to-end from hardware to intelligent solution Business Matters 40% IMPROVEMENT in first contact resolution 50% REDUCTION in call transfer rate 16% IMPROVEMENT in agent utilisation 100% PROTECTION of legacy system investment Challenge Matching caller requests to agent’s skills The client sought to increase the performance of its inbound contact centre, matching each caller request to the most expert agent, based on the agent’s personal knowledge of that specific request, captured from previous calls. In the client’s previous approach to this problem, the client used queue based routing and skill based routing with a hard link between people and queues or people and their skills. Contact centre cognitive routing based on previously solved cases The Loop Q cognitive appliance matches each caller request to the most expert agent. Case Study A top-tier Asian Telecommunications provider was facing a customer support issue with its outdated call queue-based routing technology solution. Long customer wait times and employee frustration threatened their quality of customer support offerings. Loop Q was able to utilise the dark data associated with previous calls, managed by each agent, to automatically and continuously determine each agent’s unique micro-skills. Using cognitive determination it would then match each caller request to the ideal agent. Taking only a very short time to roll out the project; the partner was able to lightly and quickly integrate Loop Q and retrofit it on top of the legacy systems already in place.
2

Contact centre cognitive routing based on previously ...€¦ · Contact centre cognitive routing based on previously . solved cases. The Loop Q cognitive appliance matches each .

May 21, 2020

Download

Documents

dariahiddleston
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Contact centre cognitive routing based on previously ...€¦ · Contact centre cognitive routing based on previously . solved cases. The Loop Q cognitive appliance matches each .

IndustryTelecommunications

ObjectiveRadically increase the performance of the inbound contact centre by matching each caller request to the agent with the best expertise; based on the agent’s personal knowledge and past experiences.

ApproachInstead of the skills-based approach that is so typical for call centres, the approach was based on the agent’s personal knowledge of that specific request, captured from previous calls. A beneficial side effect; this method eliminates the need to manually update every agent’s HR/ skills profile every time they learn new skills.

IT Matters• Learn any language, directly from a

client’s call centre data

• Autonomous learning and reasoning, which runs on a customised plug and play HPC appliance

• Leverage the Loop Q platform also with self-learning cognitive S/W robots

• Cognitively-retrofit all your legacy systems with a single platform

• End-to-end from hardware to intelligent solution

Business Matters• 40% IMPROVEMENT in first contact

resolution

• 50% REDUCTION in call transfer rate

• 16% IMPROVEMENT in agent utilisation

• 100% PROTECTION of legacy system investment

Challenge

Matching caller requests to agent’s skillsThe client sought to increase the performance of its inbound contact centre, matching each caller request to the most expert agent, based on the agent’s personal knowledge of that specific request, captured from previous calls.

In the client’s previous approach to this problem, the client used queue based routing and skill based routing with a hard link between people and queues or people and their skills.

Contact centre cognitive routing based on previously solved casesThe Loop Q cognitive appliance matches each caller request to the most expert agent.

Case Study

A top-tier Asian Telecommunications provider was facing a customer support issue with its outdated call queue-based routing technology solution. Long customer wait times and employee frustration threatened their quality of customer support offerings.

Loop Q was able to utilise the dark data associated with previous calls, managed by each agent, to automatically and continuously determine each agent’s unique micro-skills. Using cognitive determination it would then match each caller request to the ideal agent.

Taking only a very short time to roll out the project; the partner was able to lightly and quickly integrate Loop Q and retrofit it on top of the legacy systems already in place.

Page 2: Contact centre cognitive routing based on previously ...€¦ · Contact centre cognitive routing based on previously . solved cases. The Loop Q cognitive appliance matches each .

Cognitive Solution

Automatically determining each agent’s micro-skills Loop Q is language-independent, understanding any dialect or language. This includes: Chinese, Japanese, Korean, Arabic, in addition to machine languages, such as IoT standards. This is extremely important for organisations with a global reach.

The appliance automatically determines each agent’s micro-skills, from their previous call information. Using each agent’s micro-skills, it then matches each caller request to the most appropriate agent. The Loop Q cognitive appliance pairs perfectly with the HPE Apollo 6500, ensuring an excellent combination to run this solution.

Dark data used for learning phase: Two years of historical calls Dark data used for reasoning phase: New calls

Benefit

Requests directly sent to the most qualified expert40% improvement in first contact resolution: requests are sent directly to a subject matter expert who has received and successfully processed similar requests.

50% reduction in transfer rate: there is no need to forward calls to multiple experts, one expert is all you need to have your question managed.

By utilising the agents skills more efficiently, agents are happier at work. They are best suited for the requests they are processing, ensuring that customers are getting the best support available.

Customer at a glanceAsian Telecommunication OperatorOne of the leading three full service communications providers in Asia. They offer a suite of mobile voice-and-data communication services over their network, including fixed broadband and fibre broadband services.

Application• Artificial Intelligence & Deep Learning

Hardware• Apollo 6500 Gen9

• Hosting up to 8 P100 and 256 GB of RAM, using 2690V4 processors

LoopAI Labs HPC appliance• Powered by GPUs and scales from

8,000 cores up to 40,000 cores

• Up to eight appliances clustered using Infiniband, addressing high-demand processing tasks

Software• Loop Q, Loop AI Labs’ unsupervised

human-capacity cognitive computing platform is designed to be general purpose, enabling endless possibilities for implementing various cognitive applications across all industries

• Learning on the dark data of two years of historical calls, the partner implemented an application that recognises and reasons on the incoming call centre requests

Learn more athpe.com

© Copyright 2018 Hewlett Packard Enterprise Development LP. The information contained herein is subject to change without notice. The only warranties for Hewlett Packard Enterprise products and services are set forth in the express warranty statements accompanying such products and services. Nothing herein should be construed as constituting an additional warranty. Hewlett Packard Enterprise shall not be liable for technical or editorial errors or omissions contained herein.

a00039283enw, January 2018

Case Study IndustryAsian Telecom TelecommunicationsOperator

“The journey from an idea to a pilot, the pilot to the cognitive application, is actually surprisingly short with our unsupervised platform. The longest and most delicate step is defining KPI’s, and making sure that you have selected the best data for your Q Robot to learn from.”

- Andrea Pitrone, VP of Customer Success, Loop AI Labs

Sign up for updates

Make the right purchase decision. Click here to chat with our presales specialists.