Top Banner
PaaS Partner Community Forum 2017 Chatbots Split | March 27, 2017 Léon Smiers
14

Understanding conversations within chatbots

Apr 06, 2017

Download

Software

Leon Smiers
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: Understanding conversations within chatbots

PaaS Partner Community Forum 2017ChatbotsSplit | March 27, 2017Léon Smiers

Page 2: Understanding conversations within chatbots

2Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Léon Smiers

Oracle Solution Architect

Dutch Capgemini Center of Excellence lead Oracle PaaS

Oracle ACE

Author Oracle Case Management Solutions

http://oraclecasemanagementsolutions.com/

Page 3: Understanding conversations within chatbots

3Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

From interaction to conversation

Chatbots deliver Conversation capabilities

with Customers We need to understand

‘old fashioned Grammar’ again

Page 4: Understanding conversations within chatbots

4Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

A new sound in the market

Page 5: Understanding conversations within chatbots

5Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

My bicycle is stolen

How many ways are there to say ‘My bicycle is stolen’

My bicycle is stolen My bike is stolen Somebody took my tandem My bike got nicked My wheels are gone F**#!, they took me iron horse During the act of drinking a nice beer a rascal took advantage of me enjoying that particular beer and relieved

me of my dear bicycle, god bless his soul

Page 6: Understanding conversations within chatbots

6Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Back to school

I love grammar

Page 7: Understanding conversations within chatbots

7Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Natural Language Processing (NLP)

Parse question and determine what’s

being asked

Identify candidate answers

Score candidate answers

Return top scoring answers

Page 8: Understanding conversations within chatbots

8Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Conversation maturity model

Use Case

Interaction

Integration

Languages

Channel

Conversation span

NLP supportEase of set up

1.0

Alleviating call center and supports desks from all standard questions

menu basedSimple Q&A

Data retrieval

English + ..One or more available in productCustomer coding

Conversation stays in one channels

Simple rules (hardcoded)Coding

2.0

Automated intelligent communication

Intelligent conversationsingle line NLP

API based

Multi

Omni

Conversation can cross channels

Training model(s)Configure

3.0

Intelligent Case management

Case context

API based / vocabulary based

Flexibility in adding languages

Omni

Conversation can cross channelsMulti person conversationMulti bot interactions

Self learningPrefab

Conversation maturity level

Page 9: Understanding conversations within chatbots

9Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Where is Oracle with Chatbots?

Larry announces chatbots at Oracle Open World

A-Team launched intermediate chatbot solution in November 2016

Oracle is developing Oracle Intelligent BotsDue summer 2017

Page 10: Understanding conversations within chatbots

10Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

The Oracle Chatbot – architectureA-Team solution

Facebook Slack

Chatbot message platform

Chatbot Engine

Chatbot Components

Cloud systems

On-prem system

Chat Channel

OracleChatbot

Application

Back-end systems

Channels through which end-users can communicate

The translation engine through which messages are passed on to

the different chat channels

The core part of the chatbot application responsible for the conversation with the end-user

Communication to the back-end systems, enabling in-flight data

enrichment of conversation

The back-end systems, whether cloud or on-premise based

ACCS

MCS

Applicaton Container Cloud Services (ACCS)

Mobile Cloud Services (MCS)

Maturity level 1.0 ChatbotGood for demo’sEasy setup, good description

Page 11: Understanding conversations within chatbots

Copyright © 2017, Oracle and/or its affiliates. All rights reserved. Copyright © 2017, Oracle and/or its affiliates. All rights reserved.

Oracle Intelligent Bots: Key Components

Channel Configurator

DialogFlow

Execution

CustomComponents

in Dialog Flow

AI Engine

• Unified cross-channel chat interface between bots & humans

• Declarative bot builder UI for bot flow

• State machine that executes context driven workflows with scoped variables

• Active machine learning algorithms that identify relationships and extract insights from unstructured data

• SDK to consume backend API’s that satisfy human requests via the bot

Custom

11

Waiting for first test versionMaturity level 2.0 Chatbot ???

Page 12: Understanding conversations within chatbots

12Copyright © Capgemini and Sogeti 2016. All Rights Reserved

Presentation Title | Date

Demo

Page 13: Understanding conversations within chatbots

13Copyright © Capgemini and Sogeti 2016. All Rights Reserved

PaaS Community Platform 2017, Split Croatia, March 2017

Contact information

Léon SmiersOracle Solution ArchitectOracle ACE

[email protected]+31 6 150 30 373

http://twitter.com/leonsmiershttp://www.capgemini.com/oraclebloghttp://oraclecasemanagementsolutions.com/

Page 14: Understanding conversations within chatbots

The information contained in this presentation is proprietary.Copyright © 2016 Capgemini and Sogeti. All rights reserved.

Rightshore® is a trademark belonging to Capgemini.

www.capgemini.comwww.sogeti.com

About Capgemini and Sogeti

With more than 180,000 people in over 40 countries, Capgemini is a global leader in consulting, technology and outsourcing services. The Group reported 2015 global revenues of EUR 11.9 billion. Together with its clients, Capgemini creates and delivers business, technology and digital solutions that fit their needs, enabling them to achieve innovation and competitiveness. A deeply multicultural organization, Capgemini has developed its own way of working, the Collaborative Business Experience™, and draws on Rightshore®, its worldwide delivery model.

Learn more about us at www.capgemini.com.

Sogeti is a leading provider of technology and software testing, specializing in Application, Infrastructure and Engineering Services. Sogeti offers cutting-edge solutions around Testing, Business Intelligence & Analytics, Mobile, Cloud and Cyber Security. Sogeti brings together more than 23,000 professionals in 15 countries and has a strong local presence in over 100 locations in Europe, USA and India. Sogeti is a wholly-owned subsidiary of Cap Gemini S.A., listed on the Paris Stock Exchange.