Telephony bot
Pilot for the automation of DODO Pizza's contact center
«Dodo Pizza» is a pizzeria chain, one of the largest catering chains in Russia.
Automate the processing of some calls to the «Dodo Pizza» contact center.
Client
Task
Solution
A bot that understands what customers are saying and helps them whenever possible.
Service presentation for «Dodo» at Conversations conference in november 2019.
ABOUT
ABOUT
ABOUT
ABOUT
ABOUT
ABOUT
What our bot can do
01/
Answer customer quiestions who have already placed an order.
Make changes to the order, if possible.
Switch to operator if it cannot help.
The bot warns the operator and transmits information to him about the call
If a client asks to switch to a pizzeria manager, the bot first repeats the client's first phrase to the manager.
Basic skills
Extra skills
Call topics
02/
15%
20%
35%
30%
questions about the delivery area
questions about current orders
other questions
questions about pizzerias
The appeals that the bot has learned to handle
03/
Courier late complaint
Want to change your payment method
Make changes to delivery options
Order cancellation
Product quality complaint
How does the voice bot work
The client calls «Dodo Pizza» and gets on the robot
The bot transcribes the client's response and examines the received text
Dodo IS transfers customer data to the bot (if he has already made an order)
Based on this data, the bot determines the topic of the appeal.
The systems answers customers with a response or directs them to a operator
The client is satisfied
04/
Interesting fact
«Connect with the emperor»
A phrase that «broke» the Dodo bot system due to an error in speech recognition.
General scheme of automation of CC
05/
Telephony
Сhatbot engine
Telephony
Voice menu
Speech2Text
Dodo IS API
Intent classifier
Bot script
Text2Speech
Operator
Client
Client
We launched the initial bot for DODO as a pilot, which was a little "raw" We improved the service throughout the process by analyzing actual exchanges between bots and real customers.
Bot development process
06/
Reviewed contact center agent guides
We listened to the recordings of over 300 «operator-client» conversations
Structuring data, collecting statistics
Compiled a classifier of intents - call topics
We worked out the scripts of the «client-bot» dialogues
Integrated with Dodo IS * and customer telephony
Step 01
Step 02
Step 03
Step 05
Step 06
Step 07
Highlighted topics of conversation that needed to be automated
Step 04
preparatory stage
main stage
Transferred to development
*Dodo IS - "Dodo Pizza" information system which supports Dodo website and application. It is used by franchisers and operators of the@nbsp;contact center.
Economy
07/
2
7
15%
250 000
minutes
rubles per minute
calls per month
average duration of a conversation between a client and an operator
average cost of a contact center operator
of the work of a contact center can really be automated
getting calls to the Dodo Pizza contact center
> 500 000
rubles per month
Total
Saving DoDo Pizza money within the framework of our pilot project.
Tools
08/
We used the following services in our work:
A simple and convenient platform for developing chatbots, voice assistants and contact center automation systems.
The AI service for chatbots analytics provides a detailed assessment of their effectiveness.
zDialog
OneDash
Difficulties of the project
09/
Problem
Problem
Problem
Decision
Decision
Decision
We knew nothing about the work of the contact center.
There was no data to train the chatbot with. We chose not to transcibe recorded conversation which saved both time and money.
While working on the project, some topics of appeal became irrelivent
The bot made speech recognition errors in 46% of cases.
Problem
Decision
We have updated the bot knowledge base.
We replaced the voice recognition platform and settled on Yandex SpeechKit.
We used typical phrases that customers say. They were written by the operators of the contact center.
To reduce the risk of error, we asked «Dodo» as much information as possible.
Quotes
10/
Alexey Medvedovsky
leader of the IT direction of the contact center "Dodo Pizza"
«We had a lot of competence in the development of chatbots, but we had no idea how a contact center operated ».
«Before we met EORA, we had no idea what chatbots and artificial intelligence were».
Roman Doronin
CEO «EORA»
Results
12/
As part of a pilot project, the bot learned
successfully conduct and end a call
recognize the subject of the appeal in
67%
97%
of cases
of cases
among them
The pilot's launch was successful, and the bot's accuracy increased as more data was collected. The service started working in full-fledged mode.
We are satisfied! And the pizza is really tasty :)
See the case
«How «Dodo Pizza» benefited from contact center automation»
«How «Dodo Pizza» benefited from contact center automation»
Contact us
PRODUCTS
SECTIONS
STUDIOS
Russia, Innopolis, st. Universitetskaya, 7
2023 © EORA. All right reserved